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

    Neuronpedia

    INDEX
    Explanations

    comments and documentation within code

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

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.71
     يتيمه
    -0.71
    PerformLayout
    -0.69
    istoitu
    -0.64
     dAtA
    -0.61
    ніципа
    -0.61
    +#+#
    -0.59
     препратки
    -0.59
    keyColumn
    -0.59
     الاطلاع
    -0.58
    POSITIVE LOGITS
     eenig
    0.40
    MessageTagHelper
    0.35
     серия
    0.33
     umgekehrt
    0.32
     AppBar
    0.32
     indruk
    0.30
     серии
    0.30
    dientemente
    0.30
     Puritans
    0.29
    abstract
    0.29
    Act Density 0.004%

    No Known Activations