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

    Neuronpedia

    INDEX
    Explanations

    thoughtful and sincere questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inferiority
    0.80
     सियासी
    0.80
     médioc
    0.80
     supremacy
    0.78
    acept
    0.78
     orthodoxy
    0.78
     scandals
    0.76
     inférieurs
    0.76
     inférieure
    0.76
    ျေး
    0.75
    POSITIVE LOGITS
     thoughtful
    1.07
     sincere
    1.02
     really
    0.98
    非常
    0.95
     very
    0.91
     sincerely
    0.90
     sensitive
    0.88
     considerate
    0.88
     conscientious
    0.88
     responsible
    0.82
    Act Density 0.147%

    No Known Activations