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

    Neuronpedia

    INDEX
    Explanations

    Varied, seemingly random texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asse
    -0.31
    穹
    -0.28
    lage
    -0.28
    arda
    -0.27
     advised
    -0.27
    vana
    -0.27
    æŀģå°ij
    -0.26
    زÙħ
    -0.26
     Plenty
    -0.26
    ä»Ļå¢ĥ
    -0.26
    POSITIVE LOGITS
     unw
    0.29
    æľ¬è´¨ä¸Ĭ
    0.28
     subprocess
    0.26
    ertz
    0.26
    _Sub
    0.26
     submerged
    0.26
     reput
    0.25
    closed
    0.25
    è¾IJå°Ħ
    0.25
     shorter
    0.25
    Act Density 0.900%

    No Known Activations