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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ものは
    0.57
    ocap
    0.57
    ことは
    0.56
    出来的
    0.53
     sacro
    0.53
     Sache
    0.52
    場合は
    0.52
     यामध्ये
    0.51
    어나
    0.51
     Bezirk
    0.51
    POSITIVE LOGITS
     ষ
    0.66
    ף
    0.64
    ໊
    0.64
    相应的
    0.63
     experimentado
    0.63
    মুক্তি
    0.63
    $<
    0.61
     fainting
    0.61
    qy
    0.60
    fx
    0.60
    Act Density 0.000%

    No Known Activations