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

    Neuronpedia

    INDEX
    Explanations

    .pg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     covariance
    -0.07
     numbering
    -0.07
    ]);↵
    -0.07
    istrov
    -0.07
     Ken
    -0.06
    BP
    -0.06
     Champion
    -0.06
     smrti
    -0.06
     cult
    -0.06
    ryptography
    -0.06
    POSITIVE LOGITS
     --------------------------------------------------------------------------↵
    0.07
    альная
    0.07
    €™
    0.07
    iminary
    0.07
    ::::::::::::::
    0.06
    (trace
    0.06
     قلب
    0.06
    #----------------------------------------------------------------------------
    0.06
    _^
    0.06
    .Popup
    0.06
    Act Density 0.001%

    No Known Activations