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

    Neuronpedia

    INDEX
    Explanations

    readiness, position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	time
    -0.07
    ержав
    -0.07
     twee
    -0.06
    득
    -0.06
     싸
    -0.06
     faithful
    -0.06
    仕
    -0.06
     pilgrimage
    -0.06
     Documentary
    -0.06
    ertz
    -0.06
    POSITIVE LOGITS
     komplex
    0.07
     Functional
    0.07
     psychotic
    0.06
     आत
    0.06
     geg
    0.06
     dign
    0.06
    งแต
    0.06
     Москов
    0.06
     Duo
    0.06
     gifs
    0.06
    Act Density 0.431%

    No Known Activations