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

    Neuronpedia

    INDEX
    Explanations

    start of quotes or specific enclosed text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    1.17
     iaitu
    1.09
    तुरंग
    1.01
    crafted
    1.00
     curbing
    0.98
    йки
    0.97
    cargar
    0.97
    م
    0.95
     دادن
    0.94
    ≲
    0.93
    POSITIVE LOGITS
     difícil
    0.93
    ெல்லாம்
    0.87
    irs
    0.83
    '[
    0.83
    ような
    0.83
     ursprünglich
    0.82
    itt
    0.81
    ția
    0.80
    ल्पनिक
    0.80
     sự
    0.79
    Act Density 0.020%

    No Known Activations