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

    Neuronpedia

    INDEX
    Explanations

    programming language constructs and syntax

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

    operators followed by code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.36
     števil
    -0.36
     Jehová
    -0.36
     verticales
    -0.35
    hæng
    -0.35
    ----</
    -0.35
     vocales
    -0.35
     satunya
    -0.34
     moindre
    -0.34
     acompañado
    -0.33
    POSITIVE LOGITS
    Tembelea
    0.64
     ddelwed
    0.60
    <unused28>
    0.59
    [@BOS@]
    0.59
    igma
    0.59
    <unused41>
    0.59
    <unused74>
    0.59
    <unused17>
    0.58
    <unused14>
    0.58
    <unused8>
    0.58
    Act Density 0.011%

    No Known Activations