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

    Neuronpedia

    INDEX
    Explanations

    code filenames and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     then
    -1.87
     mismos
    -1.70
    ſſen
    -1.63
    がこの
    -1.61
     it
    -1.60
     этом
    -1.59
    側の
    -1.59
     this
    -1.58
     rano
    -1.58
     kuchen
    -1.56
    POSITIVE LOGITS
     даже
    2.06
    Spesifikasi
    2.03
    Pengertian
    1.99
     Even
    1.95
     Often
    1.77
    Even
    1.77
     حتی
    1.77
     ответить
    1.75
    мл
    1.75
     When
    1.74
    Act Density 0.028%

    No Known Activations