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

    Neuronpedia

    INDEX
    Explanations

    Numerical calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /format
    -0.07
    lund
    -0.06
     novel
    -0.06
     Payments
    -0.06
    тр
    -0.06
    ää
    -0.06
    cent
    -0.06
    concept
    -0.06
    ø
    -0.06
     Oc
    -0.06
    POSITIVE LOGITS
     meta
    0.07
     jugg
    0.07
     circumcision
    0.07
     系
    0.07
    そんな
    0.07
     業
    0.06
    ارش
    0.06
     Iterate
    0.06
    िज
    0.06
     ____
    0.06
    Act Density 0.032%

    No Known Activations