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

    Neuronpedia

    INDEX
    Explanations

    respond to commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lng
    0.45
     сорти
    0.44
    ⎙
    0.44
    컥
    0.43
     واضح
    0.41
    ก็
    0.41
     автора
    0.41
    DLJ
    0.40
    ิตร
    0.40
     नंबर
    0.40
    POSITIVE LOGITS
    >×</
    0.52
    ികി
    0.52
     například
    0.49
     disen
    0.48
     câteva
    0.47
     koniec
    0.46
    at
    0.45
     clasp
    0.44
     hasn
    0.44
     em
    0.44
    Act Density 0.001%

    No Known Activations