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

    Neuronpedia

    INDEX
    Explanations

    moksha, moco, mox

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +}^{
    0.43
    MTAB
    0.39
    jahr
    0.39
     المث
    0.37
     मेथ
    0.36
     Red
    0.34
     מז
    0.34
    Recommendation
    0.34
     vyš
    0.33
    Myth
    0.33
    POSITIVE LOGITS
    dif
    0.38
    ault
    0.38
    Mil
    0.36
    修理
    0.36
     mil
    0.36
    trl
    0.36
     raport
    0.36
     proposito
    0.36
     Mil
    0.35
    aryn
    0.35
    Act Density 0.010%

    No Known Activations