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

    Neuronpedia

    INDEX
    Explanations

    Figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amid
    -0.07
    aryawan
    -0.07
     Memories
    -0.06
    くらい
    -0.06
    .extend
    -0.06
     Hats
    -0.06
    *D
    -0.06
     memories
    -0.06
    яж
    -0.06
     stereo
    -0.06
    POSITIVE LOGITS
     Figure
    0.12
    Figure
    0.12
    figure
    0.09
     figure
    0.09
    rvé
    0.07
    cre
    0.07
    isphere
    0.07
    icom
    0.07
    पर
    0.07
     hammer
    0.07
    Act Density 0.002%

    No Known Activations