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

    Neuronpedia

    INDEX
    Explanations

    reaching the bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کوئی
    0.45
    oucí
    0.43
     Dekker
    0.40
     هیڅ
    0.40
    Política
    0.40
     Moran
    0.39
     Picker
    0.39
    λαδή
    0.39
     pięk
    0.39
     तित
    0.38
    POSITIVE LOGITS
    rees
    0.41
    tree
    0.40
    soph
    0.40
    宝
    0.40
     seem
    0.38
    frees
    0.36
     በት
    0.36
    牙
    0.35
     obey
    0.35
    `
    0.35
    Act Density 0.001%

    No Known Activations