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

    Neuronpedia

    INDEX
    Explanations

    scientific/academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anut
    -0.28
    UMP
    -0.27
    oste
    -0.27
    ecer
    -0.26
    赶ä¸Ĭ
    -0.26
    ãĥ©ãĥ³ãĤ¹
    -0.25
    acula
    -0.25
     screwed
    -0.25
    owing
    -0.25
    acha
    -0.25
    POSITIVE LOGITS
    åĬ³åĬ¨èĢħ
    0.30
     subt
    0.28
    æĢª
    0.27
    leen
    0.26
     ideal
    0.26
    纸
    0.25
    羣
    0.25
     memor
    0.25
     dominance
    0.25
    lio
    0.25
    Act Density 0.031%

    No Known Activations