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

    Neuronpedia

    INDEX
    Explanations

    awareness of facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    概
    0.38
    概念
    0.37
    InputField
    0.37
    othelial
    0.37
    ORIG
    0.36
    кость
    0.36
    佺
    0.36
    基督
    0.36
    Comparing
    0.35
    explanation
    0.35
    POSITIVE LOGITS
     knows
    0.60
     know
    0.54
     instinctively
    0.54
     Knows
    0.53
     rhythms
    0.53
     pace
    0.52
     moods
    0.52
     knew
    0.52
     languages
    0.52
     psychology
    0.52
    Act Density 0.010%

    No Known Activations