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

    Neuronpedia

    INDEX
    Explanations

    the start of a document or section header

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

    Mathematical or symbolic expressions

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.65
    Rohy
    -0.55
    ("")
    -0.55
     ''
    -0.51
     bal
    -0.51
    +"'
    -0.49
     нему
    -0.48
    ('');
    -0.48
     Mili
    -0.47
     typelib
    -0.47
    POSITIVE LOGITS
     ſtand
    0.86
    enterOuterAlt
    0.85
     greateſt
    0.81
     diſt
    0.80
     chofe
    0.79
     ſtate
    0.77
     ſta
    0.77
     reaſon
    0.75
    archiw
    0.74
     ſy
    0.74
    Act Density 0.302%

    No Known Activations