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

    Neuronpedia

    INDEX
    Explanations

    you to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     probabilidad
    0.60
    龅
    0.54
    ను
    0.51
     posición
    0.47
     consiguió
    0.47
     último
    0.46
     película
    0.46
    为例
    0.45
     quedaría
    0.45
     сайты
    0.44
    POSITIVE LOGITS
    ಕರ್
    0.46
    cumin
    0.46
    brough
    0.43
    괴
    0.43
    몰
    0.43
    וו
    0.43
    袮
    0.42
    teurs
    0.42
    abolic
    0.41
    int
    0.40
    Act Density 0.000%

    No Known Activations