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

    Neuronpedia

    INDEX
    Explanations

    specific references to subcategories and types within a broader classification system

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

    list item b

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.73
    WaitGroup
    -0.66
     utafitiHapana
    -0.66
     MainAxisSize
    -0.63
     ſind
    -0.63
    Diweddarwch
    -0.61
     Administrativna
    -0.61
    Tikang
    -0.60
    -0.60
     صوتيه
    -0.59
    POSITIVE LOGITS
    <bos>
    0.64
     c
    0.48
    ivotopis
    0.46
    dań
    0.45
     circunstancias
    0.45
     b
    0.45
     fapt
    0.43
     mattina
    0.42
     gravidanza
    0.42
     tepi
    0.42
    Act Density 0.067%

    No Known Activations