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

    Neuronpedia

    INDEX
    Explanations

    blue, red, amber light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Woman
    0.65
     Water
    0.62
     R
    0.61
     this
    0.59
     woman
    0.59
     einer
    0.58
     Explorer
    0.58
     na
    0.57
     English
    0.57
     Research
    0.57
    POSITIVE LOGITS
    克斯
    0.51
    роб
    0.50
    ቦች
    0.50
    拉斯
    0.49
    ائج
    0.49
    大家好
    0.48
    ต้
    0.48
    囟
    0.48
    흡
    0.48
    मराह
    0.48
    Act Density 0.021%

    No Known Activations