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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters or formatting symbols

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

    Code, symbols, or uncommon characters

    np_acts-logits-general · gemini-2.0-flash

    symbols and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vectorielles
    -0.66
     RIPRODUZIONE
    -0.59
     духовке
    -0.53
     internacionais
    -0.52
     alrededores
    -0.52
    Referencie
    -0.51
     cremallera
    -0.51
    marginVertical
    -0.51
     brancas
    -0.50
     especiais
    -0.49
    POSITIVE LOGITS
    <bos>
    0.84
     tartalomajánló
    0.70
    下载附件
    0.68
     Signalez
    0.67
    QMetaType
    0.63
     imageNamed
    0.61
    medriver
    0.60
    IsContent
    0.60
    agrama
    0.59
    новниш
    0.58
    Act Density 1.234%

    No Known Activations