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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whipping
    -0.07
     STREAM
    -0.07
     Royale
    -0.07
     fram
    -0.07
    wid
    -0.06
     poj
    -0.06
    AndServe
    -0.06
    _kel
    -0.06
    dess
    -0.06
     дод
    -0.06
    POSITIVE LOGITS
     Detector
    0.07
     draggable
    0.07
     ac
    0.07
    Au
    0.06
     asym
    0.06
    bootstrap
    0.06
    ٬
    0.06
    .showMessage
    0.06
    іб
    0.06
     `,↵
    0.06
    Act Density 0.002%

    No Known Activations