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

    Neuronpedia

    INDEX
    Explanations

    numbers and characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Azer
    -0.08
     AIR
    -0.08
     Liebe
    -0.08
    .reporting
    -0.08
     Mosaic
    -0.08
     Macro
    -0.07
    蜜
    -0.07
    quela
    -0.07
     equilibr
    -0.07
    Reported
    -0.07
    POSITIVE LOGITS
     slender
    0.11
     narrow
    0.11
    Straight
    0.10
     straight
    0.10
     drawn
    0.10
     straighten
    0.10
     vertical
    0.09
    線
    0.09
     elong
    0.09
     Straight
    0.09
    Act Density 0.021%

    No Known Activations