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

    Neuronpedia

    INDEX
    Explanations

    code structures and syntax elements in programming language snippets

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

    code block end characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.49
    cP
    -0.38
     RCS
    -0.38
    complexContent
    -0.38
    -0.37
     winch
    -0.36
    anias
    -0.35
     puff
    -0.35
     surla
    -0.35
     tent
    -0.35
    POSITIVE LOGITS
    DockStyle
    0.75
     betweenstory
    0.75
    تقاوى
    0.70
     ComVisible
    0.58
    WebVitals
    0.58
    EDEFAULT
    0.57
     للمعارف
    0.54
     pungkas
    0.53
     TestBed
    0.50
     noDo
    0.50
    Act Density 0.001%

    No Known Activations