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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating occurrences of names or important topics being referenced or discussed

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

    bringing up topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    baiki
    -0.33
     asesor
    -0.33
     básica
    -0.32
     escaleras
    -0.32
     explicación
    -0.32
     básico
    -0.32
     Zwar
    -0.31
     artesanía
    -0.30
     amico
    -0.30
     visión
    -0.30
    POSITIVE LOGITS
     mention
    0.86
    Mention
    0.85
     Mention
    0.83
     Mentions
    0.79
    mention
    0.77
     mentioning
    0.77
     Mentioned
    0.75
     mentions
    0.74
    提及
    0.71
     mentioned
    0.69
    Act Density 0.092%

    No Known Activations