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

    Neuronpedia

    INDEX
    Explanations

    references to elements in JSON structures

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

    programming elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hunne
    -0.53
    rô
    -0.52
    zczegól
    -0.48
    [-\
    -0.48
    ÑO
    -0.47
     Penga
    -0.45
    GRANTED
    -0.45
    seits
    -0.45
     ancha
    -0.45
    inSlope
    -0.44
    POSITIVE LOGITS
    Element
    2.70
     Element
    2.13
    ELEMENT
    1.43
     ELEMENT
    1.36
     element
    1.34
     ElementRef
    1.24
    Elemento
    1.16
    element
    1.16
    getElement
    1.14
     Elements
    1.09
    Act Density 0.003%

    No Known Activations