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

    Neuronpedia

    INDEX
    Explanations

    xx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mus
    -0.08
     Giovanni
    -0.07
    ouse
    -0.07
    UEL
    -0.07
    c
    -0.07
     vol
    -0.07
    ريب
    -0.07
     descending
    -0.07
    璁
    -0.07
     reaching
    -0.07
    POSITIVE LOGITS
    xx
    0.07
    __.'/
    0.07
    cxx
    0.07
     charm
    0.07
    ¯¯
    0.07
    国有资产
    0.07
    _InitStruct
    0.07
     الكمبي
    0.06
    (xx
    0.06
    限制
    0.06
    Act Density 0.005%

    No Known Activations