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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and syntax

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

    email addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rolling
    -0.39
     Rol
    -0.38
    Rolling
    -0.36
    Rol
    -0.35
    sup
    -0.35
     supreme
    -0.35
     rolled
    -0.35
     Pil
    -0.34
    forRoot
    -0.34
     Spraw
    -0.34
    POSITIVE LOGITS
     propOrder
    0.66
     nahilalakip
    0.63
     esternos
    0.62
     мәкал
    0.61
     itſelf
    0.59
    الإنجليزية
    0.59
     Италијани
    0.58
     fieldNum
    0.58
     pleaſure
    0.57
     betweenstory
    0.57
    Act Density 0.007%

    No Known Activations