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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jud
    -0.07
    shared
    -0.06
     one
    -0.06
    _median
    -0.06
    	common
    -0.06
    р
    -0.06
     rare
    -0.06
    li
    -0.06
     kidneys
    -0.06
    \Has
    -0.06
    POSITIVE LOGITS
     Kenny
    0.07
    =batch
    0.07
    }'↵
    0.06
     الش
    0.06
    ров
    0.06
    >-->↵
    0.06
    clc
    0.06
     πλα
    0.06
    ,'#
    0.06
    GLOSS
    0.06
    Act Density 0.800%

    No Known Activations