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

    Neuronpedia

    INDEX
    Explanations

    "],"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ㆍ동
    -0.07
    ूह
    -0.07
     vyž
    -0.07
    .setdefault
    -0.07
     тоб
    -0.07
     точно
    -0.06
    dataset
    -0.06
    .AUTO
    -0.06
    (New
    -0.06
    _OR
    -0.06
    POSITIVE LOGITS
     pours
    0.07
     všem
    0.07
     людям
    0.06
    她们
    0.06
    _OFFSET
    0.06
    �m
    0.06
     مسائل
    0.06
     Pharm
    0.06
     craftsm
    0.06
    油
    0.06
    Act Density 0.011%

    No Known Activations