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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _release
    -0.06
     Flyers
    -0.06
     č
    -0.06
     jobject
    -0.06
     маль
    -0.06
     바이
    -0.05
     진짜
    -0.05
     мис
    -0.05
    ulator
    -0.05
    以前
    -0.05
    POSITIVE LOGITS
    	End
    0.07
    Organization
    0.07
     diversity
    0.07
     broad
    0.07
    ----------
    0.07
     presidency
    0.07
    016
    0.07
    ashington
    0.07
     historia
    0.07
     д
    0.07
    Act Density 0.042%

    No Known Activations