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

    Neuronpedia

    INDEX
    Explanations

    philosophy and philosophers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.65
     vigilancia
    0.64
    다고
    0.63
    ens
    0.63
    í
    0.63
     सतर्क
    0.63
    ous
    0.59
    េង
    0.58
     газа
    0.58
     покрытия
    0.57
    POSITIVE LOGITS
     philosophy
    0.87
     filosofia
    0.85
     philosophies
    0.84
     Philosophy
    0.84
     Philosophie
    0.81
     философии
    0.80
     philosophers
    0.79
     philosophical
    0.76
     Filosof
    0.74
     philosopher
    0.73
    Act Density 0.631%

    No Known Activations