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

    Neuronpedia

    INDEX
    Explanations

    intermediate levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    僌
    0.80
     مراسم
    0.76
     manually
    0.72
     initially
    0.71
     режим
    0.71
     manual
    0.70
     regimen
    0.68
     режима
    0.67
     mindset
    0.66
     manualmente
    0.66
    POSITIVE LOGITS
     Inter
    1.13
    Intermediate
    1.06
     Intermediate
    1.05
     INTER
    1.02
     advancing
    0.97
     Advanced
    0.97
     intermediate
    0.94
     Advance
    0.92
     avanzando
    0.90
     Senior
    0.90
    Act Density 0.068%

    No Known Activations