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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Life
    -0.07
     Statue
    -0.07
    .username
    -0.06
    date
    -0.06
    كية
    -0.06
     دستور
    -0.06
    -century
    -0.06
     Crossing
    -0.06
     Cylinder
    -0.06
    REAK
    -0.06
    POSITIVE LOGITS
    っち
    0.07
    <Int
    0.07
     explorer
    0.07
    /use
    0.06
     pure
    0.06
    ℃
    0.06
    (',');↵
    0.06
    φι
    0.06
    -[
    0.06
    dispatcher
    0.06
    Act Density 0.067%

    No Known Activations