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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     varying
    -0.07
     Mercy
    -0.06
     """
    -0.06
     ст
    -0.06
    _SEC
    -0.06
     свящ
    -0.06
    :'
    -0.06
     Sporting
    -0.06
     IDD
    -0.06
     Toys
    -0.06
    POSITIVE LOGITS
     ут
    0.08
    566
    0.07
    duğunu
    0.07
     degraded
    0.06
    im
    0.06
    elson
    0.06
     ışık
    0.06
    ？」↵↵
    0.06
     prescribed
    0.06
    lim
    0.06
    Act Density 0.005%

    No Known Activations