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
     phí
    -0.08
    Auto
    -0.07
     restaur
    -0.06
    (players
    -0.06
    教授
    -0.06
    .How
    -0.06
     ώρα
    -0.06
    ωνα
    -0.06
     User
    -0.06
    _country
    -0.06
    POSITIVE LOGITS
     Skin
    0.08
     cuckold
    0.06
     indiscrim
    0.06
    overlay
    0.06
    θν
    0.06
    交易
    0.06
    (JSON
    0.06
    シア
    0.06
    0.06
     "|"
    0.06
    Act Density 0.007%

    No Known Activations