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

    Neuronpedia

    INDEX
    Explanations

    .view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	begin
    -0.07
    _WORK
    -0.06
     vk
    -0.06
     independ
    -0.06
     readily
    -0.06
     en
    -0.06
     ベ
    -0.06
     probably
    -0.06
    comput
    -0.06
    _chk
    -0.06
    POSITIVE LOGITS
    .view
    0.25
     '%$
    0.08
    hof
    0.07
    uestos
    0.07
    би
    0.07
     viele
    0.07
     회
    0.07
     mặt
    0.07
    Rates
    0.06
     Maul
    0.06
    Act Density 0.001%

    No Known Activations