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

    Neuronpedia

    INDEX
    Explanations

    retard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _node
    -0.06
     kişisel
    -0.06
     Gaussian
    -0.06
    Solution
    -0.06
    /response
    -0.06
    .vis
    -0.06
    oss
    -0.06
    していた
    -0.06
    kHz
    -0.06
    $key
    -0.05
    POSITIVE LOGITS
     retard
    0.11
     retarded
    0.10
    ragon
    0.07
     Marino
    0.07
    }}{{
    0.07
     scandals
    0.07
     Zusammen
    0.07
     ESC
    0.07
     scav
    0.07
     pals
    0.07
    Act Density 0.001%

    No Known Activations