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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è§Ĥ
    -0.27
    WN
    -0.26
    å®ŀä½ĵåºĹ
    -0.25
    ziel
    -0.25
    Oops
    -0.25
    æĿIJ
    -0.25
    eyJ
    -0.25
    earn
    -0.25
     Furn
    -0.25
    ANGUAGE
    -0.24
    POSITIVE LOGITS
    inputs
    0.26
     inputs
    0.25
    è¾ĥå¤ļ
    0.25
    onom
    0.24
    opal
    0.24
    è¿Ļä¹Ī说
    0.24
     pyl
    0.23
    åı£æ°´
    0.23
    chor
    0.23
    credit
    0.23
    Act Density 2.182%

    No Known Activations