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

    Neuronpedia

    INDEX
    Explanations

    the presence of numerical values or statistical data

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

    LaTeX mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.79
     ſehen
    -0.77
     indígen
    -0.75
     Infór
    -0.73
    ſſung
    -0.72
     surla
    -0.72
     increí
    -0.71
     müſſen
    -0.71
    iſchen
    -0.69
    ſicht
    -0.69
    POSITIVE LOGITS
    \
    0.59
    았
    0.52
    <bos>
    0.51
    1
    0.49
     I
    0.47
    The
    0.47
     \
    0.45
    5
    0.44
    .
    0.43
    2
    0.41
    Act Density 0.000%

    No Known Activations