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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and measurements

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

    comparisons and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reverso
    -0.43
    verwijspagina
    -0.43
    Obras
    -0.43
    Personendaten
    -0.43
    bunch
    -0.43
    ंदीखरीदारी
    -0.42
    ResumeLayout
    -0.42
    章节错误
    -0.42
     архивлан
    -0.41
     bunch
    -0.41
    POSITIVE LOGITS
    ExtendWith
    0.43
    TargetException
    0.40
     dioses
    0.36
     vů
    0.36
    transQ
    0.36
    ühungen
    0.35
    lanatory
    0.35
    哚
    0.35
     conmigo
    0.35
     tegens
    0.35
    Act Density 0.063%

    No Known Activations