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

    Neuronpedia

    INDEX
    Explanations

    math, lists, studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anye
    -0.31
    çıŃ
    -0.29
    CTR
    -0.28
    roys
    -0.28
    åĬ¡
    -0.27
    SPELL
    -0.26
    edBy
    -0.26
    lesh
    -0.25
    abus
    -0.24
    ãĥ¬ãĤ¹
    -0.24
    POSITIVE LOGITS
    arel
    0.27
    æľªå©ļ
    0.26
    è¢ħ
    0.25
    western
    0.25
     onStart
    0.24
    è¹Ĭ
    0.24
    çľĭä¸įåĩº
    0.24
    éĵ¿
    0.24
     kostenlos
    0.24
    ga
    0.24
    Act Density 0.019%

    No Known Activations