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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	RTE
    -0.07
     büyük
    -0.07
    RTL
    -0.07
     yanında
    -0.06
     зни
    -0.06
    _RADIO
    -0.06
     ü
    -0.06
    ับต
    -0.06
    ประกาศ
    -0.06
     дія
    -0.06
    POSITIVE LOGITS
     zoo
    0.07
     Resume
    0.07
    ufact
    0.06
    	cin
    0.06
     Rig
    0.06
     according
    0.06
     Albert
    0.06
     Healing
    0.06
     Additionally
    0.06
    -cart
    0.06
    Act Density 0.013%

    No Known Activations