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

    Neuronpedia

    INDEX
    Explanations

    ng

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     січ
    -0.07
     davidjl
    -0.07
     Tob
    -0.06
     Siz
    -0.06
     NOTIFY
    -0.06
    家伙
    -0.06
    endale
    -0.06
    氧
    -0.06
     Tanner
    -0.06
     카지노
    -0.06
    POSITIVE LOGITS
    (settings
    0.07
    unexpected
    0.07
    _ng
    0.07
     Net
    0.07
     In
    0.07
    yleft
    0.07
     صنعت
    0.07
    --+
    0.07
     болезни
    0.07
    lightly
    0.06
    Act Density 0.004%

    No Known Activations