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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to systems and their components

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

    technical components and devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.94
    出版年
    -0.89
     للمعارف
    -0.80
    verifyException
    -0.79
    ſicht
    -0.74
     TestBed
    -0.73
    حوالہ
    -0.73
     メンテナ
    -0.72
    iſche
    -0.71
     パンチラ
    -0.70
    POSITIVE LOGITS
    之一
    0.31
     wezen
    0.29
     tegens
    0.29
    談社
    0.28
     miłości
    0.27
    corazón
    0.26
     relatório
    0.26
    听说
    0.26
    难怪
    0.25
    CN
    0.25
    Act Density 0.064%

    No Known Activations