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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (BigDecimal
    -0.07
     phim
    -0.06
    partial
    -0.06
    第
    -0.06
     methyl
    -0.06
    [parent
    -0.06
     března
    -0.06
     galer
    -0.06
     Barn
    -0.06
    '>{
    -0.06
    POSITIVE LOGITS
     use
    0.17
     USE
    0.15
     Use
    0.14
    Use
    0.13
     used
    0.13
     uses
    0.12
    -use
    0.11
     Used
    0.11
     using
    0.11
     용
    0.11
    Act Density 0.410%

    No Known Activations