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

    Neuronpedia

    INDEX
    Explanations

    refresh

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilité
    -0.08
    焊
    -0.07
     zipper
    -0.07
     Vue
    -0.07
    ∱
    -0.07
     esper
    -0.07
     vows
    -0.07
    _NB
    -0.07
    (ang
    -0.07
     Buen
    -0.06
    POSITIVE LOGITS
    (credentials
    0.09
    std
    0.08
    0.07
    .Dictionary
    0.07
     democrat
    0.07
    HEAD
    0.07
    token
    0.07
    刷卡
    0.06
    地下水
    0.06
    Controller
    0.06
    Act Density 0.006%

    No Known Activations