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

    Neuronpedia

    INDEX
    Explanations

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.43
     모두
    0.39
    이트
    0.38
    UnitPrice
    0.35
     동시에
    0.34
     District
    0.34
     다른
    0.34
     기타
    0.34
     Ait
    0.33
     한
    0.33
    POSITIVE LOGITS
     விமர்
    0.48
     compleja
    0.45
    z
    0.43
    ié
    0.42
    f
    0.42
     nové
    0.42
    em
    0.42
     variantes
    0.41
     críticas
    0.41
    u
    0.41
    Act Density 0.251%

    No Known Activations