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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regexp
    -0.08
     Constructs
    -0.08
     Dtype
    -0.08
     جميع
    -0.08
    ㅅ
    -0.07
     EACH
    -0.07
     Retro
    -0.07
    .squareup
    -0.07
    _CLOSE
    -0.07
     '{@
    -0.07
    POSITIVE LOGITS
     الع
    0.07
    海外市场
    0.07
    יגה
    0.07
    _operation
    0.07
    让大家
    0.07
    ес
    0.07
    加热
    0.07
    aga
    0.06
    era
    0.06
     하
    0.06
    Act Density 0.061%

    No Known Activations