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

    Neuronpedia

    INDEX
    Explanations

    yl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cheesy
    -0.07
    するために
    -0.07
     DU
    -0.07
    .Tele
    -0.07
    九十
    -0.07
    .Di
    -0.07
     Investigations
    -0.07
    isify
    -0.07
    历来
    -0.06
     Venezuela
    -0.06
    POSITIVE LOGITS
    ☈
    0.08
    lobals
    0.07
    Receiver
    0.07
    ::::::::
    0.07
    优秀
    0.07
    ואה
    0.07
    尧
    0.06
    륭
    0.06
    bins
    0.06
     unbelie
    0.06
    Act Density 0.007%

    No Known Activations