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

    Neuronpedia

    INDEX
    Explanations

    Berlin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owntown
    -0.07
     thirsty
    -0.07
     foremost
    -0.06
    	ax
    -0.06
     issu
    -0.06
     되
    -0.06
     GROUP
    -0.06
    onClick
    -0.06
     TIM
    -0.06
    .pm
    -0.06
    POSITIVE LOGITS
     Berlin
    0.08
    Berlin
    0.07
     berlin
    0.07
    latin
    0.06
    annot
    0.06
    зи
    0.06
    lín
    0.06
     наш
    0.06
    emade
    0.06
    .Manifest
    0.06
    Act Density 0.006%

    No Known Activations