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

    Neuronpedia

    INDEX
    Explanations

    D or R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Weekend
    -0.07
    odní
    -0.07
     believable
    -0.06
     Civic
    -0.06
     nucleus
    -0.06
    second
    -0.06
    289
    -0.06
     gimm
    -0.06
    CreateInfo
    -0.06
     weekend
    -0.06
    POSITIVE LOGITS
    (CON
    0.07
    填
    0.07
     풍
    0.06
    :)↵
    0.06
     treasury
    0.06
    尼
    0.06
     Dh
    0.06
     '↵
    0.06
     replic
    0.06
     Downing
    0.06
    Act Density 0.003%

    No Known Activations