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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Button
    -0.07
    .Package
    -0.07
    --------------
    -0.07
     finite
    -0.07
     Constraint
    -0.06
    gregation
    -0.06
    buz
    -0.06
     Note
    -0.06
    /library
    -0.06
    Feature
    -0.06
    POSITIVE LOGITS
     nét
    0.07
    สมาช
    0.07
    �
    0.07
     positives
    0.06
    iche
    0.06
    егист
    0.06
    042
    0.06
    initWith
    0.06
    매
    0.06
    .Focused
    0.06
    Act Density 0.029%

    No Known Activations