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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᠴ
    -0.07
    Iterations
    -0.07
    脱贫
    -0.07
    (namespace
    -0.07
    ocs
    -0.07
    edback
    -0.07
    	bytes
    -0.06
    (d
    -0.06
    cess
    -0.06
     everyday
    -0.06
    POSITIVE LOGITS
     Germany
    0.08
     GBP
    0.07
    统一
    0.07
    最初的
    0.07
    Separator
    0.07
    OR
    0.07
     Ма
    0.07
    	ui
    0.07
    议员
    0.07
     Style
    0.07
    Act Density 0.007%

    No Known Activations