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

    Neuronpedia

    INDEX
    Explanations

    Statistics and percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qua
    -0.07
    quan
    -0.06
    equ
    -0.06
    olid
    -0.06
    liqu
    -0.06
    Distribution
    -0.06
     divisions
    -0.06
     Sweat
    -0.06
    abl
    -0.06
    aturally
    -0.06
    POSITIVE LOGITS
    clist
    0.06
     Rupert
    0.06
    talya
    0.06
    ير
    0.06
    .guild
    0.06
     scale
    0.06
    IZE
    0.06
    _vec
    0.06
     Gly
    0.06
    .iloc
    0.06
    Act Density 0.060%

    No Known Activations