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

    Neuronpedia

    INDEX
    Explanations

    showerror messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ğın
    1.93
    RSSI
    1.71
    ﺱ
    1.66
    ﺗ
    1.62
    skiego
    1.61
     habitually
    1.60
     hjust
    1.51
    ECTION
    1.51
     jazdy
    1.49
    😍😍
    1.49
    POSITIVE LOGITS
    きた
    1.55
    ות
    1.53
    ка
    1.48
    これ
    1.45
     toată
    1.42
    ान
    1.38
    ली
    1.37
    स्ट
    1.35
    ্যান
    1.33
     graft
    1.33
    Act Density 0.000%

    No Known Activations