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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging actions or recommendations

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

    recommendations and "if you" statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝟹
    -0.40
     dàng
    -0.39
    TokenNameDOT
    -0.33
     Iš
    -0.32
     Progress
    -0.31
    幸いです
    -0.30
     disambiguazione
    -0.29
    Shift
    -0.29
    Sending
    -0.29
     setIs
    -0.29
    POSITIVE LOGITS
     nahilalakip
    0.60
    Kaynakça
    0.57
    oneofs
    0.52
    SequentialGroup
    0.52
    richTextPanel
    0.51
    addPreferredGap
    0.51
    LookAnd
    0.51
    httphttps
    0.48
    AnchorTagHelper
    0.48
    XmlSchema
    0.48
    Act Density 0.008%

    No Known Activations