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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections or segments in the text

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

    let followed by variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numberWith
    -0.60
    wpdb
    -0.59
     đích
    -0.58
     везе
    -0.57
    orosi
    -0.57
    invokeLater
    -0.56
    targeted
    -0.56
     tartalomajánló
    -0.56
     calculées
    -0.56
    cstdlib
    -0.56
    POSITIVE LOGITS
    __":
    0.52
     Voici
    0.50
    tagext
    0.50
    RTLR
    0.48
    ftagPool
    0.47
     seguente
    0.47
     कथ
    0.47
     ctx
    0.47
    ctx
    0.46
     Jerusalén
    0.45
    Act Density 0.248%

    No Known Activations