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

    Neuronpedia

    INDEX
    Explanations

    AI identity as model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     physicochemical
    0.43
     bytecode
    0.41
     compaction
    0.40
     chromatographic
    0.40
     analysis
    0.39
     schema
    0.38
     bitmap
    0.38
     capacitor
    0.38
     quantitative
    0.38
     biochemical
    0.38
    POSITIVE LOGITS
    Honestly
    0.40
    ừng
    0.40
    我现在
    0.39
    ohia
    0.39
     prijatel
    0.38
    我自己
    0.38
     എന്റെ
    0.37
    ઈ
    0.37
    addle
    0.37
    ara
    0.36
    Act Density 0.136%

    No Known Activations