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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sentences or sections

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

    Appears before numbers or names

    np_acts-logits-general · gemini-2.0-flash

    technical procedures and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.73
    NewUrlParser
    -0.66
     '\\;'
    -0.63
    pired
    -0.58
    UrlResolution
    -0.55
     виправивши
    -0.55
    neurial
    -0.52
    irical
    -0.51
     dõi
    -0.51
    Gruss
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.60
    はじめに
    0.60
    jspx
    0.57
     none
    0.57
     ComVisible
    0.56
    InjectAttribute
    0.55
    Cons
    0.55
    ContentAsync
    0.53
    None
    0.53
    clientY
    0.52
    Act Density 0.068%

    No Known Activations