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

    Neuronpedia

    INDEX
    Explanations

    numerical and mathematical expressions

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

    Numbers inside parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    mechanical hardness, professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.87
     مشين
    -0.74
    CloseOperation
    -0.67
    rungsseite
    -0.63
     <<<<<<<<<<<<<<
    -0.62
    ]--;
    -0.61
    DebuggerStep
    -0.60
    enumii
    -0.60
    {}{}
    -0.60
    Diwedd
    -0.59
    POSITIVE LOGITS
     Atherton
    0.46
     geweest
    0.45
     rendent
    0.44
     muualla
    0.44
     Spicer
    0.44
    Retention
    0.43
     Unidas
    0.43
     arabe
    0.42
    spół
    0.42
     goû
    0.42
    Act Density 0.229%

    No Known Activations