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

    Neuronpedia

    INDEX
    Explanations

    assess situations and risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.89
     Сим
    0.84
    sb
    0.82
    ۹
    0.82
     Бен
    0.80
    coupled
    0.78
    sp
    0.77
    ia
    0.76
     Лу
    0.76
    sobre
    0.75
    POSITIVE LOGITS
    ל
    0.90
    ב
    0.85
     rating
    0.85
     valutazione
    0.83
    2
    0.82
     assess
    0.82
    '
    0.82
     evaluate
    0.80
    л
    0.80
     değerlend
    0.79
    Act Density 0.047%

    No Known Activations