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

    Neuronpedia

    INDEX
    Explanations

    medical regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🅢
    -0.08
     através
    -0.07
    (Art
    -0.07
     jeżeli
    -0.07
    明ら
    -0.07
    utowired
    -0.07
    _timezone
    -0.07
     קונ
    -0.06
     initWithNibName
    -0.06
    琛
    -0.06
    POSITIVE LOGITS
     looking
    0.08
    פורט
    0.07
     fought
    0.07
    	build
    0.07
    -ish
    0.07
    父亲
    0.07
    路虎
    0.07
    source
    0.07
    出
    0.07
     whats
    0.06
    Act Density 0.017%

    No Known Activations