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

    Neuronpedia

    INDEX
    Explanations

    indications of clarity and certainty in statements

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

    visibility or clarity

    np_acts-logits-general · gemini-2.0-flash

    obvious, clear, evident

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     automatiquement
    -0.70
     interchangeably
    -0.62
     başına
    -0.61
     muere
    -0.60
     Marsden
    -0.57
    bbero
    -0.57
     automaticamente
    -0.57
     automatiques
    -0.56
     Kapelle
    -0.55
     inesperado
    -0.54
    POSITIVE LOGITS
     clearly
    0.94
    clearly
    0.91
    Clearly
    0.86
     Clearly
    0.84
    VIOUS
    0.76
     evident
    0.73
     obvious
    0.72
    obvious
    0.69
    :][
    0.69
    idać
    0.68
    Act Density 0.139%

    No Known Activations