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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    往
    -0.07
     Mood
    -0.07
     stirred
    -0.07
    れ
    -0.07
     Hydra
    -0.07
    bits
    -0.07
     couples
    -0.07
    柔软
    -0.06
    Eu
    -0.06
    く
    -0.06
    POSITIVE LOGITS
    itive
    0.07
    老年
    0.07
     textile
    0.07
    	util
    0.06
    鉴
    0.06
    elseif
    0.06
     civil
    0.06
    lord
    0.06
    مصلحة
    0.06
     IID
    0.06
    Act Density 0.001%

    No Known Activations