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

    Neuronpedia

    INDEX
    Explanations

    it wasn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    1.12
    щены
    1.08
     aguda
    1.05
    ro
    1.04
    ColorScheme
    1.04
    ták
    1.03
    hasta
    1.02
    ؤ
    1.00
    레
    1.00
     constituer
    0.98
    POSITIVE LOGITS
     поради
    1.01
    challenged
    1.00
    GPI
    1.00
    従
    0.99
     μ
    0.99
    Celtic
    0.97
    ulph
    0.95
    asteroid
    0.94
     г
    0.92
    ене
    0.92
    Act Density 0.000%

    No Known Activations