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

    Neuronpedia

    INDEX
    Explanations

    TV show episode titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     also
    0.51
     furthermore
    0.48
     CII
    0.45
     Oil
    0.44
     oil
    0.44
    butyl
    0.43
     Zayed
    0.43
     ਮ
    0.42
     speciale
    0.42
    And
    0.42
    POSITIVE LOGITS
    咾
    0.54
    ऎ
    0.46
     cryptic
    0.45
    ث
    0.44
     Кто
    0.44
     ደቂ
    0.44
     потрі
    0.44
    ابق
    0.44
    Prothorax
    0.44
    答
    0.44
    Act Density 0.002%

    No Known Activations