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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rick
    -0.10
     Korn
    -0.09
    Rick
    -0.09
     музы
    -0.08
     साह
    -0.08
    dream
    -0.08
     Dick
    -0.08
    旅
    -0.07
     Jana
    -0.07
     Mushroom
    -0.07
    POSITIVE LOGITS
     behe
    0.08
    157
    0.07
     aktual
    0.07
     മൊ
    0.07
    �
    0.07
    线路
    0.07
     leh
    0.07
     tempo
    0.07
     aank
    0.07
     auprès
    0.07
    Act Density 0.002%

    No Known Activations