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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åıįèĢĮ
    -0.28
    иÑĩеÑģк
    -0.27
    dre
    -0.27
     ego
    -0.26
     Republic
    -0.26
    å©Ĭ
    -0.25
     nond
    -0.25
    ึà¸ģ
    -0.25
     morning
    -0.25
     didSet
    -0.25
    POSITIVE LOGITS
    azole
    0.30
    лез
    0.27
     verd
    0.25
    Atlas
    0.25
    oce
    0.25
    æŁľ
    0.24
     Greenwood
    0.24
    è¹Ħ
    0.24
    WithOptions
    0.24
    ä¸ŃéĢĶ
    0.23
    Act Density 0.034%

    No Known Activations