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
     resembl
    -0.08
     ﾞ
    -0.07
     نماز
    -0.06
    DEFAULT
    -0.06
     coerce
    -0.06
    blr
    -0.06
     cref
    -0.06
    HIR
    -0.06
     lineno
    -0.06
    iliyor
    -0.06
    POSITIVE LOGITS
     Зап
    0.07
    -launch
    0.07
     salesman
    0.07
     electron
    0.06
    _EC
    0.06
    Companies
    0.06
    Init
    0.06
     Opposition
    0.06
     kob
    0.06
     briefing
    0.06
    Act Density 0.002%

    No Known Activations