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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers and their fraction representations

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

    statistical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })*/
    -0.48
    .*")]
    -0.48
     Od
    -0.47
    ellant
    -0.46
    mybatisplus
    -0.46
    Packard
    -0.45
    EFIAPI
    -0.45
    berra
    -0.45
    lotl
    -0.43
    onius
    -0.43
    POSITIVE LOGITS
     TextAlign
    0.45
    
    0.41
    RTHOOK
    0.35
     majority
    0.35
    Herzlich
    0.34
    majority
    0.34
    UnsafeEnabled
    0.33
    encodeWith
    0.32
     meeste
    0.32
    Lähteet
    0.31
    Act Density 0.158%

    No Known Activations