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

    Neuronpedia

    INDEX
    Explanations

    references to rankings and positions among entities or categories

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

    rankings and superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.50
    聙
    -0.49
    oplasty
    -0.49
     Wicidata
    -0.48
    iſen
    -0.48
    nosaurus
    -0.47
    ðsíða
    -0.47
    🦵
    -0.47
    supposed
    -0.46
    -0.46
    POSITIVE LOGITS
     Económica
    0.33
    AutoScaleMode
    0.31
     independiente
    0.30
    #
    0.29
    KURZBESCHREIBUNG
    0.29
     يتيمه
    0.29
     gén
    0.28
     yyl
    0.28
     Ráp
    0.28
    InputBorder
    0.28
    Act Density 0.029%

    No Known Activations