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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.75
    ת
    0.57
    ↵
    0.55
    z
    0.55
    л
    0.55
    es
    0.54
    in
    0.52
    er
    0.52
    ა
    0.50
    ل
    0.49
    POSITIVE LOGITS
     of
    0.54
    (
    0.50
    ется
    0.50
     on
    0.46
    {
    0.44
     was
    0.42
    ension
    0.42
     at
    0.41
     ={
    0.39
    ிகள்
    0.37
    Act Density 0.394%

    No Known Activations