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

    Neuronpedia

    INDEX
    Explanations

    backtick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     řed
    -0.07
    .Di
    -0.07
     gourmet
    -0.07
    .Minimum
    -0.07
    .hasOwnProperty
    -0.06
    Continue
    -0.06
     mirac
    -0.06
     Moderator
    -0.06
     boil
    -0.06
    .''↵↵
    -0.06
    POSITIVE LOGITS
    _DET
    0.07
     ออนไลน
    0.07
     alıp
    0.06
    Carol
    0.06
     일정
    0.06
    .edit
    0.06
     ήταν
    0.06
    Firefox
    0.06
     iyileş
    0.06
     hist
    0.06
    Act Density 0.023%

    No Known Activations