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

    Neuronpedia

    INDEX
    Explanations

    descriptions of products and their features

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

    archaic spellings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пой
    -0.26
    (
    -0.25
    řevě
    -0.25
     quelconque
    -0.25
     sonno
    -0.25
    heitsbild
    -0.24
     ninguno
    -0.24
     guapos
    -0.24
    wuchs
    -0.23
     cursed
    -0.23
    POSITIVE LOGITS
     iNdEx
    0.82
     يتيمه
    0.72
     faſt
    0.71
     pleaſure
    0.69
    RTEE
    0.69
    ſelf
    0.69
     itſelf
    0.68
    :✨
    0.68
     raiſ
    0.66
     MainAxisSize
    0.65
    Act Density 0.133%

    No Known Activations