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

    Neuronpedia

    INDEX
    Explanations

    types of controls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    2.17
    いた
    1.93
    ка
    1.73
    ના
    1.70
    స్‌
    1.67
    ä
    1.66
    us
    1.63
     destacados
    1.59
    ının
    1.58
    ドレス
    1.57
    POSITIVE LOGITS
    ség
    1.59
    y
    1.57
    europe
    1.55
    centos
    1.55
    лег
    1.50
    klassen
    1.49
    i
    1.47
    e
    1.42
    žne
    1.41
    yoga
    1.40
    Act Density 0.000%

    No Known Activations