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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a text

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

    legal terms, laws, or court cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jgl
    -0.63
    /
    -0.57
     فريبيس
    -0.54
    ãi
    -0.53
     volont
    -0.52
    öhnen
    -0.52
     égard
    -0.52
     Мексичка
    -0.51
     cadena
    -0.50
    rua
    -0.50
    POSITIVE LOGITS
     Majefty
    0.82
     Tories
    0.74
     Unito
    0.72
    ſelf
    0.72
     Dems
    0.71
     Shakspeare
    0.70
    دانشنامهٔ
    0.68
     Jove
    0.67
     Egli
    0.67
     himſelf
    0.67
    Act Density 0.154%

    No Known Activations