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

    Neuronpedia

    INDEX
    Explanations

    crisis and catastrophic events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    2.01
    CHEMY
    1.80
     знаком
    1.75
    べき
    1.70
    हरी
    1.67
    োগ
    1.66
    rocin
    1.65
    很多
    1.65
    수록
    1.64
     מאוד
    1.64
    POSITIVE LOGITS
     ensued
    2.16
    tabular
    2.02
    袭击
    1.83
     plotly
    1.80
     відбувається
    1.79
    áneamente
    1.79
     Ketika
    1.75
     ensues
    1.73
     secolo
    1.71
     averted
    1.71
    Act Density 0.249%

    No Known Activations