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

    Neuronpedia

    INDEX
    Explanations

    eye

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä¾Ľ
    -0.27
    ä»ĺ
    -0.27
    arg
    -0.26
     suppl
    -0.26
     sed
    -0.25
    æľĽ
    -0.24
     bak
    -0.24
    idelity
    -0.24
     bank
    -0.24
     sel
    -0.24
    POSITIVE LOGITS
    groupid
    0.27
    æĢķ
    0.25
    ç¯Ŀ
    0.25
    ç¿»
    0.24
    æĿ¥è¢Ń
    0.24
    íĶ½
    0.24
    ongyang
    0.24
     Exiting
    0.24
    SHA
    0.24
    ancell
    0.24
    Act Density 0.006%

    No Known Activations