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

    Neuronpedia

    INDEX
    Explanations

    instances of quotations or reported speech

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

    Percentages or ratios

    np_acts-logits-general · gemini-2.0-flash

    percentages and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.77
    انجليز
    -0.69
    NameInMap
    -0.67
     Chwiliwch
    -0.66
    AnchorStyles
    -0.63
     Signalez
    -0.60
     ComVisible
    -0.59
    cinas
    -0.59
    ."</
    -0.59
     itſelf
    -0.58
    POSITIVE LOGITS
     yesterday
    0.51
    expandindo
    0.50
    olari
    0.48
    aris
    0.46
    出版年
    0.44
     <=",
    0.43
     phẩm
    0.42
     BoxFit
    0.41
    nextInt
    0.41
    antMatchers
    0.41
    Act Density 0.085%

    No Known Activations