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

    Neuronpedia

    INDEX
    Explanations

    rans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¸įæĺĵ
    -0.29
     tack
    -0.25
    aktu
    -0.24
    ä¸įäºĪ
    -0.24
    acht
    -0.24
    stan
    -0.24
     Neural
    -0.24
    epad
    -0.23
    UMP
    -0.23
    ahn
    -0.23
    POSITIVE LOGITS
    etable
    0.28
    ertools
    0.27
    portlet
    0.25
    lux
    0.25
     progress
    0.25
    progress
    0.25
    mul
    0.25
     progressives
    0.25
     toItem
    0.24
    åĽ½äºº
    0.24
    Act Density 0.028%

    No Known Activations