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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mani
    -0.07
    imir
    -0.06
    ‡
    -0.06
    imited
    -0.06
    -0.06
    δόν
    -0.06
    idders
    -0.06
    lere
    -0.06
     trucks
    -0.06
    "L
    -0.06
    POSITIVE LOGITS
     içeren
    0.06
    /power
    0.06
     zah
    0.06
     JsonObject
    0.06
     wol
    0.06
     содерж
    0.06
    _caps
    0.06
     thoughts
    0.06
     respectable
    0.05
     haha
    0.05
    Act Density 0.005%

    No Known Activations