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

    Neuronpedia

    INDEX
    Explanations

    wrestling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "]"
    -0.07
    瓜
    -0.07
     --------------------------------------------------------------------------------
    -0.07
     effet
    -0.07
     lục
    -0.06
    _var
    -0.06
    _iteration
    -0.06
    톤
    -0.06
    .borrow
    -0.06
    })(
    -0.06
    POSITIVE LOGITS
    .sam
    0.08
     boast
    0.07
     Prix
    0.07
    ें।↵
    0.07
    preh
    0.06
     hPa
    0.06
    conc
    0.06
     Şubat
    0.06
     Goal
    0.06
     Schneider
    0.06
    Act Density 0.013%

    No Known Activations