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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	logging
    -0.07
     histograms
    -0.07
    TableView
    -0.07
    بوب
    -0.06
    groupid
    -0.06
     hypertension
    -0.06
     blinds
    -0.06
    declaration
    -0.06
     distinct
    -0.06
    .Match
    -0.06
    POSITIVE LOGITS
     доч
    0.07
    śmy
    0.07
     当
    0.06
    ed
    0.06
    伤
    0.06
     trib
    0.06
    攝
    0.06
    累
    0.06
     №
    0.06
    inqu
    0.06
    Act Density 0.002%

    No Known Activations