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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hund
    -0.07
    ActivityIndicator
    -0.07
    _IDENT
    -0.06
     찾아
    -0.06
    erness
    -0.06
     ambassador
    -0.06
    883
    -0.06
    fclose
    -0.06
    óż
    -0.06
     eater
    -0.06
    POSITIVE LOGITS
    .DEFINE
    0.06
     Sı
    0.06
     samostat
    0.06
    ()),↵
    0.06
     ماي
    0.06
     Spider
    0.06
     indexOf
    0.06
     PropTypes
    0.06
     Morris
    0.06
    .Tensor
    0.06
    Act Density 0.065%

    No Known Activations