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

    Neuronpedia

    INDEX
    Explanations

    references to various programming constructs and types related to coding

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

    batting stats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iſen
    -1.02
     nakalista
    -0.99
     ainfi
    -0.94
    arangay
    -0.91
     Geſch
    -0.91
    ambién
    -0.90
    ientras
    -0.88
    ſcher
    -0.87
    actéristi
    -0.85
     ſeine
    -0.85
    POSITIVE LOGITS
    [toxicity=0]
    0.57
    t
    0.54
    ity
    0.52
    -
    0.50
    y
    0.50
    /
    0.47
    ing
    0.46
    _
    0.46
    \
    0.45
    0
    0.45
    Act Density 0.145%

    No Known Activations