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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IH
    -0.07
     Hakk
    -0.07
    @\
    -0.07
    7
    -0.07
    半
    -0.06
    atedRoute
    -0.06
    Ar
    -0.06
     Joshua
    -0.06
     Age
    -0.06
    า
    -0.06
    POSITIVE LOGITS
    text
    0.08
    кта
    0.07
    těl
    0.07
    *time
    0.06
    table
    0.06
    	q
    0.06
     bedtime
    0.06
     Templ
    0.06
    YLeaf
    0.06
    (fe
    0.06
    Act Density 0.003%

    No Known Activations