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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stripe
    -0.07
    )").
    -0.07
    роничес
    -0.06
     сім
    -0.06
    (connection
    -0.06
    NECTION
    -0.06
    gp
    -0.06
    성을
    -0.06
    ۶
    -0.06
     considering
    -0.06
    POSITIVE LOGITS
     tender
    0.09
     Tanner
    0.08
     ND
    0.07
     oversh
    0.07
     ‘
    0.07
     Cur
    0.07
     OR
    0.07
    #$
    0.07
     polynomial
    0.07
    ,↵↵↵
    0.07
    Act Density 0.037%

    No Known Activations