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

    Neuronpedia

    INDEX
    Explanations

    negative signs and indicators in a quantitative context

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

    Punctuation separating numbers or letters

    np_acts-logits-general · gemini-2.0-flash

    legal cases and roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.81
    .
    -0.80
     
    -0.67
    -
    -0.63
     (
    -0.60
    :
    -0.56
     in
    -0.53
    /
    -0.51
     to
    -0.49
     a
    -0.48
    POSITIVE LOGITS
    expandindo
    1.13
     itſelf
    1.10
     ་་
    1.02
     autorytatywna
    1.01
     myſelf
    1.00
     disambiguazione
    0.99
     bezeichneter
    0.94
    ^(@)
    0.93
     дописавши
    0.93
     ſind
    0.90
    Act Density 1.147%

    No Known Activations