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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sense
    -0.07
    vh
    -0.07
    诚
    -0.07
     comple
    -0.07
     xAxis
    -0.06
     Employer
    -0.06
    Entries
    -0.06
     zarar
    -0.06
    alendar
    -0.06
     CK
    -0.06
    POSITIVE LOGITS
     setLoading
    0.06
     respondsToSelector
    0.06
    -Петерб
    0.06
     dodge
    0.06
    ्तर
    0.06
     slightest
    0.06
    Pro
    0.06
    陰
    0.06
    angler
    0.06
    /layouts
    0.05
    Act Density 0.031%

    No Known Activations