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

    Neuronpedia

    INDEX
    Explanations

    license types / degree above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utens
    0.48
     ছাত্রদের
    0.47
     virtuel
    0.45
    hôte
    0.45
     じゃん
    0.44
    वार
    0.44
     ഉത്സവ
    0.44
    විත
    0.44
    }{{\
    0.43
     ቀለም
    0.43
    POSITIVE LOGITS
    ences
    0.46
    ются
    0.45
    elto
    0.44
    ளும்
    0.43
     SN
    0.42
     gears
    0.41
    ).
    0.41
    ческом
    0.41
    cale
    0.41
     других
    0.41
    Act Density 0.000%

    No Known Activations