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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _decay
    -0.07
    chie
    -0.07
    Kill
    -0.07
    キャッシ
    -0.07
     authService
    -0.07
    医治
    -0.07
    מחיר
    -0.07
    (protocol
    -0.06
    dire
    -0.06
     Kirby
    -0.06
    POSITIVE LOGITS
     resent
    0.07
    (def
    0.07
    𝘊
    0.07
     Infer
    0.07
    _TOP
    0.06
     The
    0.06
    _render
    0.06
     Float
    0.06
    NUMBER
    0.06
    %;">
    0.06
    Act Density 0.003%

    No Known Activations