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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inherit
    -0.08
    .colorbar
    -0.08
     Toolbox
    -0.07
    ième
    -0.07
    surface
    -0.07
    报废
    -0.07
    isphere
    -0.06
    .__
    -0.06
     entire
    -0.06
    מרכז
    -0.06
    POSITIVE LOGITS
    𝘠
    0.07
    @Test
    0.07
    Ể
    0.07
     October
    0.07
     Delay
    0.07
    スポー�
    0.06
    يلا
    0.06
    眼里
    0.06
     де
    0.06
    LogFile
    0.06
    Act Density 0.052%

    No Known Activations