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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     owned
    -0.07
     history
    -0.07
     originated
    -0.06
    .Txt
    -0.06
    /jquery
    -0.06
    ****************************
    -0.06
     trailed
    -0.06
     filthy
    -0.06
     partida
    -0.06
    觉得
    -0.06
    POSITIVE LOGITS
     politique
    0.07
    .removeListener
    0.07
     (;;
    0.07
    sense
    0.06
    xin
    0.06
    bcd
    0.06
    ernal
    0.06
    Looper
    0.06
    semicolon
    0.06
     Zeus
    0.06
    Act Density 0.013%

    No Known Activations