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

    Neuronpedia

    INDEX
    Explanations

    sequence connector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.09
    ون
    0.95
    िंग
    0.84
    he
    0.84
    ING
    0.84
    :
    0.80
    లో
    0.79
    al
    0.78
    {
    0.76
    (
    0.74
    POSITIVE LOGITS
    ки
    0.88
    на
    0.87
    ल
    0.81
    व
    0.80
    진다
    0.80
    ก
    0.72
    наў
    0.72
    ne
    0.71
    selves
    0.70
    ك
    0.69
    Act Density 0.032%

    No Known Activations