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

    Neuronpedia

    INDEX
    Explanations

    opt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !)
    -0.08
     While
    -0.07
    Cumh
    -0.07
    Site
    -0.07
    _authenticated
    -0.07
    je
    -0.07
     blockade
    -0.07
    天气
    -0.07
     Runs
    -0.06
    VT
    -0.06
    POSITIVE LOGITS
    (words
    0.08
     combat
    0.07
    	order
    0.07
    -debug
    0.07
    美术
    0.07
     sharpen
    0.07
    だし
    0.07
    concert
    0.06
    /API
    0.06
    angel
    0.06
    Act Density 0.003%

    No Known Activations