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

    Neuronpedia

    INDEX
    Explanations

    SLA, shopping, dollars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AS
    0.55
     Indigo
    0.50
    Indigo
    0.50
    स
    0.50
     Elba
    0.49
    alade
    0.48
     culpable
    0.47
    IBLE
    0.47
     efectiva
    0.47
    áculo
    0.46
    POSITIVE LOGITS
    frid
    0.55
    -‘
    0.51
     ExifInterface
    0.51
    킹
    0.50
     പ്രസി
    0.50
    下さい
    0.49
    kovskij
    0.49
     يمكنك
    0.49
     jihad
    0.48
    齁
    0.48
    Act Density 0.003%

    No Known Activations