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
     lawmaker
    -0.07
    :test
    -0.06
    ostream
    -0.06
     nelle
    -0.06
    -success
    -0.06
     fecha
    -0.06
     PROC
    -0.06
    emperature
    -0.06
     modification
    -0.06
    ERGY
    -0.06
    POSITIVE LOGITS
    `t
    0.07
    mpeg
    0.07
    351
    0.07
     �
    0.07
    夢
    0.06
    .Component
    0.06
    ेखत
    0.06
     самостоятель
    0.06
    Kat
    0.06
    350
    0.06
    Act Density 0.002%

    No Known Activations