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
    [left
    -0.06
     living
    -0.06
     deleted
    -0.06
     ноч
    -0.06
     Continuing
    -0.06
     comparing
    -0.06
     псих
    -0.06
     minimal
    -0.06
     surrounding
    -0.05
    -0.05
    POSITIVE LOGITS
    σκε
    0.07
     sistemi
    0.07
    caffe
    0.07
    출장안마
    0.07
    _gs
    0.07
    зації
    0.06
     içindeki
    0.06
    embed
    0.06
    cakes
    0.06
     СРСР
    0.06
    Act Density 0.049%

    No Known Activations