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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一个人
    -0.07
     STORE
    -0.07
     fizz
    -0.06
     Paid
    -0.06
     Mets
    -0.06
     cheat
    -0.06
    /location
    -0.06
    awan
    -0.06
    avanaugh
    -0.06
    енный
    -0.05
    POSITIVE LOGITS
    υσ
    0.06
    arov
    0.06
     THESE
    0.06
     notifier
    0.06
    <X
    0.06
    /lab
    0.06
     apt
    0.06
    setData
    0.06
     startPos
    0.06
    toHaveBeenCalledTimes
    0.06
    Act Density 0.016%

    No Known Activations