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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cohen
    -0.08
    éis
    -0.07
     benefited
    -0.07
     precio
    -0.06
     soutě
    -0.06
     womb
    -0.06
    ými
    -0.06
    .KeyEvent
    -0.06
     pokus
    -0.06
    47
    -0.06
    POSITIVE LOGITS
    ww
    0.08
    (pack
    0.07
    とう
    0.07
    яв
    0.07
    jak
    0.07
    APS
    0.07
    rav
    0.07
    (case
    0.06
    pal
    0.06
    �
    0.06
    Act Density 0.043%

    No Known Activations