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

    Neuronpedia

    INDEX
    Explanations

    references to studies or evaluations that highlight notable performances or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    most [adjective] [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.51
    BeginContext
    -0.51
     للمعارف
    -0.51
     SqlCommand
    -0.47
    epy
    -0.46
    oneofs
    -0.46
    RTCF
    -0.45
    ².
    -0.45
    ceğine
    -0.45
    OGND
    -0.44
    POSITIVE LOGITS
     imprimible
    0.56
     integridad
    0.52
    gól
    0.51
     vastaan
    0.50
     gravedad
    0.49
     spéciaux
    0.48
     eccell
    0.48
     cerrada
    0.46
     favorito
    0.46
     favoritos
    0.46
    Act Density 0.071%

    No Known Activations