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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols in scientific or mathematical contexts

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

    bullet points or numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.63
    tvguidetime
    -0.59
     $_(
    -0.59
    VYMaps
    -0.57
    anglès
    -0.57
     ſta
    -0.57
    ロウィン
    -0.56
    -0.56
     الرياضيه
    -0.56
    ⤻
    -0.56
    POSITIVE LOGITS
     presentato
    0.42
     civilización
    0.41
     venganza
    0.40
     nación
    0.38
     ModelExpression
    0.35
     nakalista
    0.35
     sorpresas
    0.33
     descuentos
    0.33
     votación
    0.32
     república
    0.32
    Act Density 0.001%

    No Known Activations