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

    Neuronpedia

    INDEX
    Explanations

    words starting with pass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    왑
    0.83
     classic
    0.80
    popular
    0.80
    培养
    0.77
    天
    0.76
     polynomial
    0.76
     взрос
    0.76
     pulling
    0.76
     grown
    0.76
     deco
    0.76
    POSITIVE LOGITS
    াপাশি
    1.62
     muster
    1.38
    ionate
    1.30
    ivating
    1.13
    engers
    1.13
    უხ
    1.11
    ionat
    1.09
    aic
    1.06
    ivated
    1.06
    sthrough
    1.05
    Act Density 0.114%

    No Known Activations