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

    Neuronpedia

    INDEX
    Explanations

    introducing the next step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.56
    िंग
    0.51
    ing
    0.43
    ون
    0.40
    లో
    0.40
    :
    0.39
     जोकि
    0.38
    原料
    0.38
     velv
    0.36
    ة
    0.36
    POSITIVE LOGITS
    на
    0.59
     on
    0.44
    k
    0.42
    ne
    0.40
     in
    0.40
    나
    0.40
    ก
    0.39
    за
    0.38
    selves
    0.37
    서는
    0.36
    Act Density 0.039%

    No Known Activations