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

    Neuronpedia

    INDEX
    Explanations

    exports keychain, power still

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astotal
    0.40
    方式
    0.40
     कदमों
    0.39
    Brows
    0.39
    ELL
    0.39
    TOUCH
    0.39
    स्वर
    0.38
    BUR
    0.38
    VideoButton
    0.38
    竰
    0.38
    POSITIVE LOGITS
     khoa
    0.46
     rocket
    0.43
    כת
    0.39
    څ
    0.39
     rockets
    0.38
     scientific
    0.38
    を表
    0.38
    గు
    0.38
     flash
    0.37
     chemistry
    0.37
    Act Density 0.000%

    No Known Activations