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

    Neuronpedia

    INDEX
    Explanations

    evidence experiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    泊
    -0.07
     обработ
    -0.07
     Preserve
    -0.06
    HT
    -0.06
     Comput
    -0.06
    emplace
    -0.06
     변
    -0.06
    datasets
    -0.06
    ?'↵↵
    -0.06
    ,k
    -0.06
    POSITIVE LOGITS
    lijk
    0.06
    renders
    0.06
     sen
    0.06
     throws
    0.06
     Sche
    0.06
     síd
    0.06
    -Requested
    0.06
     ราค
    0.06
    ISODE
    0.06
     beats
    0.06
    Act Density 0.029%

    No Known Activations