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
    tg
    -0.07
    ιχ
    -0.07
     handset
    -0.07
    GU
    -0.06
     투
    -0.06
     Mas
    -0.06
    (surface
    -0.06
     Cruise
    -0.06
     Colony
    -0.06
    <=(
    -0.06
    POSITIVE LOGITS
     dokument
    0.07
    oref
    0.06
    lain
    0.06
     Tweets
    0.06
     m
    0.06
    akespeare
    0.06
    分
    0.06
    CallableWrapper
    0.06
    .Designer
    0.06
    .Items
    0.06
    Act Density 0.008%

    No Known Activations