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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating speech or quotations

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

    possessive 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imagui
    -0.79
     erſt
    -0.75
     beſch
    -0.72
     الرياضيه
    -0.71
     パンチラ
    -0.71
     简谱
    -0.71
     vooz
    -0.71
    <unused52>
    -0.70
    <unused8>
    -0.70
    <unused3>
    -0.70
    POSITIVE LOGITS
     AppCompatTheme
    0.32
    s
    0.29
     and
    0.26
    ่ว
    0.25
     his
    0.25
    Ljava
    0.25
    SerializedName
    0.24
     Empres
    0.24
     jaunes
    0.22
     mision
    0.22
    Act Density 0.037%

    No Known Activations