Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    indicative symbols and formatting used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, separators, or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    corresponds to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    basicConfig
    -0.75
    HtmlAttribute
    -0.66
    ://$
    -0.57
    CodedInputStream
    -0.54
     ArrayAdapter
    -0.54
    ówczas
    -0.53
    GOTREF
    -0.50
     tarko
    -0.49
    viewDidLoad
    -0.49
    RetentionPolicy
    -0.49
    POSITIVE LOGITS
    ----------------
    0.94
    ================
    0.94
    ################
    0.87
     End
    0.85
     ==
    0.81
    ////////////////
    0.80
    END
    0.79
    ****************
    0.77
     END
    0.77
     ===
    0.77
    Act Density 0.283%

    No Known Activations