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

    Neuronpedia

    INDEX
    Explanations

    text generation web ui

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    keh
    0.41
     ケ
    0.39
    フェ
    0.37
    嗅
    0.37
     السكان
    0.36
    ケ
    0.36
     Kew
    0.35
     ке
    0.35
    㡚
    0.35
     ቀ
    0.34
    POSITIVE LOGITS
     Dram
    0.38
     bun
    0.37
    Mud
    0.37
     বন্দ্য
    0.36
     Garland
    0.35
    martin
    0.35
     J
    0.35
    XY
    0.35
     விரு
    0.35
     Zhen
    0.35
    Act Density 0.006%

    No Known Activations