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

    Neuronpedia

    INDEX
    Explanations

    good enough or rounded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ServiceClient
    0.43
    AHN
    0.43
    uduk
    0.42
    偿
    0.42
    첸
    0.42
    CCC
    0.41
    reactant
    0.41
    effectuer
    0.41
     Serviço
    0.40
    UFF
    0.40
    POSITIVE LOGITS
     alt
    0.44
     empir
    0.41
     natuurlijk
    0.41
     Enrich
    0.41
     arrête
    0.40
     alte
    0.40
     embrace
    0.40
     certaines
    0.40
     heil
    0.40
     zelfs
    0.40
    Act Density 0.001%

    No Known Activations