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

    Neuronpedia

    INDEX
    Explanations

    stop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     文
    -0.07
     соврем
    -0.07
     oud
    -0.07
    bilder
    -0.07
     Crud
    -0.07
     tính
    -0.07
     тради
    -0.06
    ิลล
    -0.06
    datal
    -0.06
     vera
    -0.06
    POSITIVE LOGITS
     stop
    0.22
     Stop
    0.18
     stopped
    0.17
     stops
    0.17
    Stop
    0.17
     stopping
    0.15
     STOP
    0.14
    stop
    0.14
    stops
    0.10
    STOP
    0.10
    Act Density 0.020%

    No Known Activations