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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns and syntax structures

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

    Digits followed by other digits

    np_acts-logits-general · gemini-2.0-flash

    numbers and hexadecimal digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ffilmiau
    -0.79
    fjspx
    -0.78
    findpost
    -0.74
    buttonBar
    -0.70
     FetchType
    -0.69
     GetEnumerator
    -0.66
     referrerpolicy
    -0.64
    Hozzáférés
    -0.61
     AspNetCore
    -0.60
    rrggbb
    -0.60
    POSITIVE LOGITS
     sanitarias
    0.59
     aynı
    0.50
    Kram
    0.48
    Hash
    0.47
    arch
    0.45
    same
    0.45
     same
    0.44
    hash
    0.44
     sval
    0.43
     mismo
    0.42
    Act Density 1.121%

    No Known Activations