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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bott
    -0.08
    	the
    -0.07
    Variant
    -0.07
    PAGE
    -0.07
     Anglo
    -0.07
    ()>↵
    -0.07
    tag
    -0.07
    -result
    -0.07
    GET
    -0.06
    ,"%
    -0.06
    POSITIVE LOGITS
     افراد
    0.06
    ennes
    0.06
     중요
    0.06
    (hand
    0.06
     Nation
    0.06
     molecules
    0.06
    ούν
    0.06
     sunshine
    0.06
     OV
    0.06
    止
    0.05
    Act Density 0.004%

    No Known Activations