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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ideologies
    0.98
     préparer
    0.96
     philosophies
    0.95
     философ
    0.93
     допомогти
    0.93
     programas
    0.93
     özel
    0.93
    他人
    0.92
     habilidades
    0.91
     cadeau
    0.90
    POSITIVE LOGITS
     maximum
    0.92
     Observed
    0.90
     approximated
    0.88
     spurious
    0.87
     Maximum
    0.87
    Maximum
    0.85
     detectable
    0.85
     detected
    0.85
     approximate
    0.82
     maksimum
    0.82
    Act Density 0.176%

    No Known Activations