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

    Neuronpedia

    INDEX
    Explanations

    elements of code related to command types and operational templates in a programming context

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

    type, group, id, bounds, width, buf, number, mask, check, instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.67
     desmotivaciones
    -0.58
     ainfi
    -0.56
     valsty
    -0.53
     lørdag
    -0.52
     competitivo
    -0.52
     conmigo
    -0.51
     mediodía
    -0.50
     pérd
    -0.49
     avoient
    -0.49
    POSITIVE LOGITS
    _
    1.02
    \_
    0.68
    {~
    0.62
    -
    0.61
    }_
    0.60
    mml
    0.57
    orithmic
    0.57
     Ber
    0.55
    orm
    0.55
    esian
    0.54
    Act Density 0.255%

    No Known Activations