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

    Neuronpedia

    INDEX
    Explanations

    PURPOSE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bug
    -0.07
     Squ
    -0.06
    player
    -0.06
     Brow
    -0.06
     srpna
    -0.06
    =G
    -0.06
     softball
    -0.06
     difficulty
    -0.06
    ilen
    -0.06
    POINTS
    -0.06
    POSITIVE LOGITS
    져
    0.07
     영화
    0.07
    elib
    0.06
    0.06
     utilizing
    0.06
    оні
    0.06
    _bool
    0.06
    玄
    0.06
     inout
    0.06
     tableName
    0.06
    Act Density 0.001%

    No Known Activations