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

    Neuronpedia

    INDEX
    Explanations

    non-english languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hacking
    0.46
    acid
    0.46
     r
    0.45
     predicts
    0.45
    r
    0.45
    nh
    0.44
     promised
    0.44
    donor
    0.44
    ston
    0.44
    nat
    0.44
    POSITIVE LOGITS
    지
    0.54
     переме
    0.52
    수
    0.52
    рти
    0.52
    情報を
    0.52
     художе
    0.51
    ку
    0.50
     процессов
    0.48
    팅
    0.46
    اء
    0.46
    Act Density 0.000%

    No Known Activations