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

    Neuronpedia

    INDEX
    Explanations

    code structure, technical terms, states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﾝ
    0.49
    шина
    0.47
     avanzar
    0.46
    Ｓ
    0.45
    નુ
    0.43
    Ｔ
    0.42
    Ｍ
    0.42
     fuente
    0.41
     scrollBody
    0.41
    рока
    0.41
    POSITIVE LOGITS
     (
    0.50
    nicht
    0.48
    ethical
    0.45
    est
    0.45
    population
    0.45
    uring
    0.44
     आदर्श
    0.44
    Mechanism
    0.44
    nie
    0.43
    mechanism
    0.43
    Act Density 0.000%

    No Known Activations