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

    Neuronpedia

    INDEX
    Explanations

    steps or process

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naciones
    0.65
    osiery
    0.63
    amentales
    0.61
    algam
    0.57
     صفحه
    0.57
    rored
    0.55
     cadenas
    0.55
    jsonObject
    0.54
     unidad
    0.54
     मुझ
    0.54
    POSITIVE LOGITS
    מים
    0.61
    kari
    0.61
    积累
    0.57
    蓊
    0.57
    大型
    0.57
    лет
    0.56
    کار
    0.56
     май
    0.55
    नी
    0.55
    鱿
    0.55
    Act Density 0.000%

    No Known Activations