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

    Neuronpedia

    INDEX
    Explanations

    state of knowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Presumably
    0.79
     silent
    0.70
    まさに
    0.68
    Gut
    0.67
     মাহমু
    0.65
    樺
    0.64
    おそらく
    0.64
     ideje
    0.63
     bonnes
    0.63
     precisely
    0.62
    POSITIVE LOGITS
     aware
    0.94
     Aware
    0.82
    Aware
    0.80
     conhecimento
    0.73
     connaissance
    0.72
     توان
    0.71
     knowledge
    0.70
     заре
    0.67
     Knowledge
    0.67
     Awareness
    0.67
    Act Density 0.001%

    No Known Activations