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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Layers
    -0.07
    Markers
    -0.06
     Однако
    -0.06
     Однак
    -0.06
     COOKIE
    -0.06
     upd
    -0.06
    	meta
    -0.06
     Loaded
    -0.06
     Hàng
    -0.05
     `"
    -0.05
    POSITIVE LOGITS
     IPC
    0.07
     إل
    0.07
    ckt
    0.07
     догов
    0.06
    itimate
    0.06
    prm
    0.06
     Perm
    0.06
    xEA
    0.06
    ronic
    0.06
     películ
    0.06
    Act Density 0.004%

    No Known Activations