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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zero
    -0.07
     HTC
    -0.07
    коном
    -0.07
    Fab
    -0.06
     издел
    -0.06
    ΑΠ
    -0.06
     рабоч
    -0.06
    玉
    -0.06
    AccessToken
    -0.06
    :".
    -0.06
    POSITIVE LOGITS
    hift
    0.06
    ','=
    0.06
    (direction
    0.06
     Haut
    0.06
    _um
    0.06
     raison
    0.06
     trench
    0.06
    isas
    0.06
    -Pro
    0.06
     stint
    0.06
    Act Density 0.001%

    No Known Activations