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

    Neuronpedia

    INDEX
    Explanations

    people affected by hardship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assailant
    0.41
    Severe
    0.40
     የማይ
    0.40
    severe
    0.38
     engaged
    0.37
     الابتدائي
    0.37
    vitro
    0.37
     uttering
    0.36
     outnumbered
    0.36
    脆弱
    0.36
    POSITIVE LOGITS
     affected
    1.05
    Affected
    1.00
     Affected
    0.95
    affected
    0.93
     impacted
    0.90
     प्रभावित
    0.87
     afectados
    0.87
     afet
    0.82
     afectadas
    0.79
     affect
    0.77
    Act Density 0.037%

    No Known Activations