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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     fancy
    -0.07
    inho
    -0.07
    社会保障
    -0.07
     בן
    -0.07
    inia
    -0.06
    Classifier
    -0.06
     hear
    -0.06
    fcc
    -0.06
    ذه
    -0.06
    igar
    -0.06
    POSITIVE LOGITS
    .clipsToBounds
    0.06
     GRID
    0.06
    Ƭ
    0.06
     bitrate
    0.06
    писание
    0.06
    ength
    0.06
     הש
    0.06
    .routing
    0.06
    美军
    0.06
    𝓽
    0.06
    Act Density 0.026%

    No Known Activations