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

    Neuronpedia

    INDEX
    Explanations

    UB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     सन
    -0.07
     matchup
    -0.07
    ))),
    -0.06
     justification
    -0.06
     Liz
    -0.06
     Mart
    -0.06
     škola
    -0.06
    chestra
    -0.06
    人才
    -0.06
     chimpan
    -0.06
    POSITIVE LOGITS
    arus
    0.09
    ombs
    0.07
    VB
    0.06
    urf
    0.06
    weed
    0.06
    uestas
    0.06
    auen
    0.06
    ucz
    0.06
     warped
    0.06
    バス
    0.06
    Act Density 0.034%

    No Known Activations