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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cheduling
    -0.08
     scouts
    -0.07
     auctions
    -0.06
    ilot
    -0.06
    (Seq
    -0.06
    ับ
    -0.06
     homage
    -0.06
    _PAYLOAD
    -0.06
    那样
    -0.06
     scalar
    -0.05
    POSITIVE LOGITS
    用品
    0.07
     dental
    0.07
     Michele
    0.07
    _pc
    0.07
    female
    0.07
     follic
    0.06
     содерж
    0.06
    /store
    0.06
    762
    0.06
    _decor
    0.06
    Act Density 0.056%

    No Known Activations