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

    Neuronpedia

    INDEX
    Explanations

    site

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unner
    -0.28
    ctest
    -0.27
    stå
    -0.26
    第ä¸ĢæĿ¡
    -0.26
     tapes
    -0.25
     goodness
    -0.25
    æ·Ģ
    -0.24
     Tac
    -0.24
    æĴ¤
    -0.24
     tac
    -0.24
    POSITIVE LOGITS
    åĴ©
    0.27
     Morph
    0.26
     giá»Ŀ
    0.26
    ensively
    0.25
    .pem
    0.25
     morph
    0.25
    "|
    0.25
    beiter
    0.24
     Zum
    0.24
    ãģ¨ãģĵãĤįãģ§
    0.24
    Act Density 0.001%

    No Known Activations