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

    Neuronpedia

    INDEX
    Explanations

    mixing substances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    区
    -0.07
     ticks
    -0.07
    สาม
    -0.07
     แพ
    -0.07
     κάθε
    -0.06
    Que
    -0.06
    ाप
    -0.06
    ighbors
    -0.06
    -times
    -0.06
    eled
    -0.06
    POSITIVE LOGITS
     trp
    0.06
     pornô
    0.06
     ↑
    0.06
    ENTS
    0.06
     vyb
    0.06
     attributes
    0.06
     جشن
    0.06
     Karen
    0.06
     رابط
    0.06
     irq
    0.06
    Act Density 0.014%

    No Known Activations