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
     invasion
    -0.07
    状态
    -0.07
     unaffected
    -0.06
    vasion
    -0.06
    uate
    -0.06
    degrees
    -0.06
     assays
    -0.06
    mann
    -0.06
     grant
    -0.06
    fü
    -0.06
    POSITIVE LOGITS
     ##
    0.21
    opt
    0.07
     모르
    0.07
    นก
    0.07
    apy
    0.07
    ic
    0.07
    \Http
    0.06
    .Scale
    0.06
    05
    0.06
    Navigation
    0.06
    Act Density 0.002%

    No Known Activations