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

    Neuronpedia

    INDEX
    Explanations

    transfer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rear
    -0.07
    timer
    -0.07
     ту
    -0.06
    फ
    -0.06
    Wal
    -0.06
    чу
    -0.06
     Lan
    -0.06
     cuk
    -0.06
     skeptic
    -0.06
    stin
    -0.06
    POSITIVE LOGITS
    ORD
    0.07
    richt
    0.06
    THEN
    0.06
    нов
    0.06
     Southwest
    0.06
    navigation
    0.06
    ätze
    0.06
     ог
    0.06
     everywhere
    0.06
    acies
    0.06
    Act Density 0.029%

    No Known Activations