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

    Neuronpedia

    INDEX
    Explanations

    cannot fulfill requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    2.36
     kunne
    2.23
    क
    2.17
    ி
    2.17
    ι
    2.13
    om
    2.03
    aks
    2.03
    c
    2.02
    об
    1.98
    up
    1.97
    POSITIVE LOGITS
    на
    2.23
    न
    1.87
     Inicio
    1.82
    郸
    1.82
     flats
    1.80
     slats
    1.77
    بتدي
    1.75
     LEAD
    1.73
     attest
    1.72
    هایی
    1.72
    Act Density 0.679%

    No Known Activations