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

    Neuronpedia

    INDEX
    Explanations

    repeated concepts or items related to groupings or classifications

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

    one of the things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তথ্যসূত্র
    -0.57
     morado
    -0.53
     kasarigan
    -0.51
     suhu
    -0.51
    óngase
    -0.50
     irré
    -0.50
     aprobado
    -0.48
    ánto
    -0.48
    Referințe
    -0.47
     soñar
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.59
    TypedDataSet
    0.58
    ReusableCell
    0.52
     egyik
    0.47
    raltar
    0.43
     histone
    0.43
     grootste
    0.42
    醐
    0.42
     أحد
    0.41
    lawayo
    0.40
    Act Density 0.001%

    No Known Activations