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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drums
    0.64
     സമര
    0.62
     Duties
    0.62
     可愛
    0.61
     Keyboard
    0.61
     Desarrollo
    0.61
    Alchemy
    0.60
    讐
    0.59
     Therapeutic
    0.58
     Licensed
    0.58
    POSITIVE LOGITS
    Lik
    0.59
    および
    0.57
     precipit
    0.57
     мате
    0.56
     어느
    0.55
    โก
    0.55
     од
    0.54
     покупа
    0.54
    elimin
    0.54
    ,|\
    0.54
    Act Density 0.000%

    No Known Activations