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

    Neuronpedia

    INDEX
    Explanations

    culture/nationality observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RUNNING
    -0.08
    Eine
    -0.07
    将来
    -0.06
    実
    -0.06
    ToLeft
    -0.06
    �
    -0.06
     clap
    -0.06
    杧
    -0.06
    onso
    -0.06
    emain
    -0.06
    POSITIVE LOGITS
    ???
    0.09
    带回
    0.07
    ERIC
    0.07
    وبة
    0.07
     horrified
    0.06
    чат
    0.06
     spotify
    0.06
     foss
    0.06
     sufferers
    0.06
    _z
    0.06
    Act Density 0.162%

    No Known Activations