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

    Neuronpedia

    INDEX
    Explanations

    transfers, typo, bruja, states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    0.47
     presso
    0.46
     smaller
    0.45
    sm
    0.44
     smok
    0.44
     typ
    0.43
    sp
    0.43
     sp
    0.43
     in
    0.43
     very
    0.43
    POSITIVE LOGITS
     huwa
    0.55
    itatea
    0.52
     निवड
    0.52
     Trần
    0.51
     новые
    0.51
     кнопки
    0.50
     étudi
    0.48
     меч
    0.48
     डिस्प्ले
    0.48
    ități
    0.48
    Act Density 0.000%

    No Known Activations