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

    Neuronpedia

    INDEX
    Explanations

    disorganized

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ŭ
    -0.07
    交错
    -0.07
    elled
    -0.07
    ered
    -0.07
     UF
    -0.07
    起身
    -0.07
     amused
    -0.06
    city
    -0.06
    -separated
    -0.06
     sez
    -0.06
    POSITIVE LOGITS
     kotlin
    0.08
    (pre
    0.07
    .html
    0.07
    _signature
    0.07
    て
    0.07
    .PackageManager
    0.07
    (depend
    0.07
     الحمل
    0.07
     불구하고
    0.07
    합니다
    0.06
    Act Density 0.159%

    No Known Activations