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

    Neuronpedia

    INDEX
    Explanations

    schedule, avoid, stop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tasarım
    0.57
     diseño
    0.54
     dibandingkan
    0.54
     likened
    0.52
     penelitian
    0.52
     postcss
    0.52
     diketahui
    0.51
    ólogo
    0.51
    ളം
    0.51
     глаз
    0.51
    POSITIVE LOGITS
     Alabama
    0.46
    項
    0.43
    ug
    0.43
    井
    0.42
    Ад
    0.41
    いた
    0.41
     Alamo
    0.41
    手
    0.41
    蜜
    0.40
    <0x8F>
    0.40
    Act Density 0.030%

    No Known Activations