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

    Neuronpedia

    INDEX
    Explanations

    Great

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handled
    -0.07
    ߍ
    -0.07
    וך
    -0.07
    _lp
    -0.07
     конструк
    -0.07
    �
    -0.07
     fileList
    -0.07
    WARDED
    -0.07
    ᐋ
    -0.07
     unfinished
    -0.07
    POSITIVE LOGITS
     grip
    0.07
    稿件
    0.07
     Chattanooga
    0.07
    /util
    0.07
    Mult
    0.07
    _comm
    0.07
    Race
    0.06
    carrier
    0.06
     Michigan
    0.06
    \<^
    0.06
    Act Density 0.138%

    No Known Activations