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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and syntax elements in code

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

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.59
     CreateTagHelper
    -0.59
    MessageTagHelper
    -0.57
     '\\;'
    -0.56
    findpost
    -0.51
     dAtA
    -0.49
     propOrder
    -0.49
    afficheront
    -0.48
    حوالہ
    -0.48
    érale
    -0.48
    POSITIVE LOGITS
     itſelf
    0.64
     raiſ
    0.52
     myſelf
    0.46
     fubject
    0.44
    }');
    0.44
     fometimes
    0.44
    !');
    0.43
     ſche
    0.42
     poffible
    0.41
    }';
    0.40
    Act Density 0.029%

    No Known Activations