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

    Neuronpedia

    INDEX
    Explanations

    excess, overreactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    níka
    -0.07
    theses
    -0.06
    WillAppear
    -0.06
     Waterproof
    -0.06
    -frame
    -0.06
    يب
    -0.06
    _Left
    -0.06
    apy
    -0.06
     cardinal
    -0.06
     Dak
    -0.06
    POSITIVE LOGITS
     ketogenic
    0.06
     retros
    0.06
    .nil
    0.06
    .Feature
    0.06
     �
    0.06
    渡
    0.06
    管理
    0.06
    支持
    0.06
     finale
    0.06
     recreational
    0.06
    Act Density 0.014%

    No Known Activations