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

    Neuronpedia

    INDEX
    Explanations

    code, HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ch
    -0.07
     Tah
    -0.07
     które
    -0.07
    _third
    -0.07
     батьків
    -0.07
     clich
    -0.06
    osa
    -0.06
    かし
    -0.06
     offices
    -0.06
     Secrets
    -0.06
    POSITIVE LOGITS
     isol
    0.06
    xmin
    0.06
    DOWN
    0.06
    看到
    0.06
     hormone
    0.06
     Wilmington
    0.06
     *↵↵
    0.06
    .GetChild
    0.06
     Decode
    0.06
     мыш
    0.06
    Act Density 0.000%

    No Known Activations