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

    Neuronpedia

    INDEX
    Explanations

    unstable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RuntimeMethod
    -0.07
     Rect
    -0.07
    uro
    -0.06
    	Rect
    -0.06
    .smart
    -0.06
     seniors
    -0.06
     revered
    -0.06
    /logger
    -0.06
     chron
    -0.06
    'я
    -0.06
    POSITIVE LOGITS
     unstable
    0.08
     instability
    0.07
     prow
    0.07
    出品
    0.06
    tti
    0.06
    méně
    0.06
    (hdr
    0.06
    атора
    0.06
     風
    0.06
    heed
    0.06
    Act Density 0.022%

    No Known Activations