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

    Neuronpedia

    INDEX
    Explanations

    elemental planes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    훔
    0.43
     अशी
    0.38
    ısıyla
    0.38
     Explore
    0.38
    និយ
    0.37
    ಹ್
    0.37
     ಏಕೆಂದರೆ
    0.36
     Blur
    0.35
    oshape
    0.35
    怠
    0.35
    POSITIVE LOGITS
    Ngày
    0.41
     politics
    0.40
     plastic
    0.39
     Ngày
    0.38
    kirk
    0.36
     plastics
    0.36
     harassing
    0.36
     active
    0.35
     aspen
    0.35
     August
    0.35
    Act Density 0.000%

    No Known Activations