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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Christmas
    -0.07
    XY
    -0.06
     motions
    -0.06
     shows
    -0.06
    /sm
    -0.06
     asympt
    -0.06
    Explorer
    -0.06
    ledi
    -0.06
     have
    -0.06
    -0.06
    POSITIVE LOGITS
    "@
    0.07
     αρ
    0.06
    ]):
↵
    0.06
    corp
    0.06
    ALLERY
    0.06
    ")->
    0.06
    mpjes
    0.06
    chunks
    0.06
     mongoose
    0.06
    tabs
    0.06
    Act Density 0.002%

    No Known Activations