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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )。
    0.74
    )
    0.71
     με
    0.66
    )!
    0.62
     )
    0.60
     publicar
    0.56
     prendere
    0.54
     ແ
    0.54
     で
    0.54
     varietà
    0.53
    POSITIVE LOGITS
    I
    0.59
    ார்த்த
    0.46
    gris
    0.46
    can
    0.46
    חיל
    0.46
     sandwiched
    0.45
    띠
    0.44
    ílio
    0.44
     bothers
    0.44
    tinger
    0.43
    Act Density 0.398%

    No Known Activations