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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     쉽게
    -0.08
     receber
    -0.07
     לקרא
    -0.07
     Spear
    -0.07
     '~
    -0.07
     الطفل
    -0.07
    紧密结合
    -0.07
     addChild
    -0.07
    開發
    -0.07
    步伐
    -0.06
    POSITIVE LOGITS
    kommen
    0.08
    LOTS
    0.07
    حوال
    0.07
    urrection
    0.07
    .coin
    0.06
    End
    0.06
    .air
    0.06
    imers
    0.06
    封
    0.06
     midterm
    0.06
    Act Density 0.013%

    No Known Activations