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

    Neuronpedia

    INDEX
    Explanations

    direct action or control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Creat
    0.48
     і
    0.48
    ț
    0.47
    Scroll
    0.47
    Parte
    0.46
     кре
    0.46
     регла
    0.46
     марки
    0.45
     ста
    0.45
     ла
    0.45
    POSITIVE LOGITS
    殘
    0.46
    ྔ
    0.46
    yty
    0.44
    нець
    0.43
    glise
    0.43
     první
    0.42
     मजदूरों
    0.42
    gres
    0.41
    ಿಂದ
    0.40
    onies
    0.40
    Act Density 0.002%

    No Known Activations