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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    children
    -0.06
     TODO
    -0.06
    .Cluster
    -0.06
    ụn
    -0.06
    歯
    -0.06
     Killing
    -0.06
    [arr
    -0.06
    _DIRECT
    -0.06
    Weather
    -0.06
    ocrates
    -0.06
    POSITIVE LOGITS
    _mA
    0.07
     denominator
    0.07
     specificity
    0.07
     防
    0.07
     Evan
    0.06
    овала
    0.06
    Come
    0.06
    .ReadOnly
    0.06
     loses
    0.06
     ),
↵
    0.06
    Act Density 0.019%

    No Known Activations