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

    Neuronpedia

    INDEX
    Explanations

    students

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ramids
    -0.07
    _null
    -0.07
     transpose
    -0.06
    Overlay
    -0.06
     accurately
    -0.06
     Bought
    -0.06
    む
    -0.06
     Yong
    -0.06
     Jerusalem
    -0.06
    .asset
    -0.06
    POSITIVE LOGITS
     glac
    0.07
    SCI
    0.07
    نتاج
    0.06
     trata
    0.06
    _expr
    0.06
     večer
    0.06
     homosexuals
    0.06
    契
    0.06
     нор
    0.06
     ^{°}
    0.06
    Act Density 0.015%

    No Known Activations