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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usable
    -0.07
     wrink
    -0.07
     erotisch
    -0.07
    _POS
    -0.06
    Phi
    -0.06
     Aw
    -0.06
     DIS
    -0.06
     thoải
    -0.06
    mods
    -0.06
     Ja
    -0.06
    POSITIVE LOGITS
    λα
    0.07
     返回
    0.06
    eka
    0.06
    洗
    0.06
    개발
    0.06
    _PARAMETER
    0.06
    ;&
    0.06
     Charts
    0.06
    检测
    0.06
     catchError
    0.05
    Act Density 0.129%

    No Known Activations