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

    Neuronpedia

    INDEX
    Explanations

    reproducibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ĥ¬
    -0.29
    åĨįçİ°
    -0.28
    ãĥĪãĥª
    -0.26
    .tpl
    -0.26
     bm
    -0.26
    license
    -0.25
    ording
    -0.25
    onic
    -0.25
     reproduce
    -0.24
     Fleet
    -0.24
    POSITIVE LOGITS
     lump
    0.27
    粤
    0.25
    eturn
    0.24
    æ¹Ľ
    0.24
    èħ»
    0.24
    #End
    0.24
     Lump
    0.24
    äºĴè¡¥
    0.24
    åIJĪè§Ħ
    0.24
     Insider
    0.23
    Act Density 0.537%

    No Known Activations