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

    Neuronpedia

    INDEX
    Explanations

    questions about when or what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    􀂾
    0.44
     gradioApp
    0.44
     womenProduct
    0.44
    沔
    0.43
    <unused395>
    0.42
     হইয়৷
    0.42
    apadani
    0.41
    Despatx
    0.41
    ورٹی
    0.41
     thumbnailUrl
    0.41
    POSITIVE LOGITS
    0.55
    ,
    0.54
      
    0.48
    ↵↵
    0.44
     -
    0.43
     (
    0.43
    -
    0.42
     U
    0.42
     and
    0.41
    .
    0.41
    Act Density 0.000%

    No Known Activations