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

    Neuronpedia

    INDEX
    Explanations

    later, straight, Duct, wheel, groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Underwater
    0.44
    <
    0.43
    byshire
    0.43
     aph
    0.41
    eta
    0.41
    Type
    0.39
    ucci
    0.39
    ant
    0.39
    apad
    0.38
    hed
    0.38
    POSITIVE LOGITS
     consecuencia
    0.51
     nome
    0.50
    캘
    0.50
     zej
    0.50
     système
    0.49
     couleur
    0.49
     забезпе
    0.49
     ಮೆ
    0.49
     سیس
    0.48
    ੱਚ
    0.48
    Act Density 0.000%

    No Known Activations