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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formal notation

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

    LaTeX math expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical norms and inequalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lewin
    -0.50
     cortinas
    -0.46
     shift
    -0.45
     part
    -0.42
    unters
    -0.42
    flap
    -0.42
     flap
    -0.42
     parte
    -0.42
    密的
    -0.42
     inc
    -0.41
    POSITIVE LOGITS
    awtextra
    0.97
     kaynağından
    0.91
     '\\;'
    0.90
    twimg
    0.88
     MainAxisSize
    0.85
    出版年
    0.82
    Hentet
    0.80
    клопе
    0.80
    WithIOException
    0.80
    AsUp
    0.79
    Act Density 0.921%

    No Known Activations