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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters

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

    conditional branches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.65
    GraphicsUnit
    -0.63
     незавершена
    -0.61
    AddTagHelper
    -0.59
     surla
    -0.58
     Normdatei
    -0.58
    RTDA
    -0.56
    IsContent
    -0.56
    fjspx
    -0.55
    ArrowToggle
    -0.54
    POSITIVE LOGITS
     otherwise
    0.66
     Otherwise
    0.58
     else
    0.57
    else
    0.57
     OTHERWISE
    0.55
     altrimenti
    0.54
    otherwise
    0.54
    Otherwise
    0.53
    elif
    0.48
     ellers
    0.48
    Act Density 0.053%

    No Known Activations