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

    Neuronpedia

    INDEX
    Explanations

    Minimal API

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ду
    0.47
    '$.
    0.47
    Ethiop
    0.47
     Capitalism
    0.45
     Bezirk
    0.45
    َّة
    0.44
     según
    0.44
     Ethiop
    0.43
    )。
    0.43
    Button
    0.42
    POSITIVE LOGITS
     batter
    0.52
     wouldn
    0.50
    珴
    0.49
     wann
    0.45
     flooring
    0.45
     fondos
    0.45
     coz
    0.45
     bother
    0.45
    အနေ
    0.44
     spanning
    0.44
    Act Density 0.000%

    No Known Activations