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

    Neuronpedia

    INDEX
    Explanations

    places and their condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    0.21
     सिस्टम
    0.20
     giới
    0.20
    تی
    0.20
    یت
    0.20
     یک
    0.20
     نے
    0.19
    たち
    0.19
     بک
    0.19
    다고
    0.19
    POSITIVE LOGITS
    h
    0.25
    ed
    0.24
    il
    0.21
    ir
    0.20
    ader
    0.20
    ப்பான்
    0.20
    em
    0.20
    vollen
    0.19
    v
    0.19
    ellent
    0.18
    Act Density 0.131%

    No Known Activations