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

    Neuronpedia

    INDEX
    Explanations

    then followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.52
    /
    0.46
    +
    0.44
    ing
    0.42
    ih
    0.40
     जिससे
    0.38
     knew
    0.38
    :
    0.38
    िंग
    0.37
    (
    0.37
    POSITIVE LOGITS
     затем
    0.70
     sitten
    0.55
     പിന്നെ
    0.54
     THEN
    0.54
     vervolgens
    0.54
     kemudian
    0.52
     потім
    0.52
    Kemudian
    0.51
     그다
    0.49
     then
    0.48
    Act Density 0.020%

    No Known Activations