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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sanctioned
    -0.07
    Dict
    -0.07
    .renderer
    -0.07
    Oops
    -0.06
     �
    -0.06
     sah
    -0.06
    Cases
    -0.06
     труд
    -0.06
    oš
    -0.06
     editText
    -0.06
    POSITIVE LOGITS
     //
↵
↵
    0.07
    =.
    0.07
     ;
↵
↵
    0.07
    |#
    0.07
    .↵↵↵↵↵↵↵↵↵↵
    0.06
    」↵↵
    0.06
    ==========↵
    0.06
    ')));↵↵
    0.06
     ||
↵
    0.06
                           ↵
    0.06
    Act Density 0.003%

    No Known Activations