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

    Neuronpedia

    INDEX
    Explanations

    xor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .buttons
    -0.08
    انی
    -0.07
     -*-↵
    -0.07
    ché
    -0.07
    _inventory
    -0.07
    ynomials
    -0.07
    gang
    -0.06
     Leben
    -0.06
    řaz
    -0.06
    اني
    -0.06
    POSITIVE LOGITS
     setShow
    0.07
     پژ
    0.07
    xor
    0.06
    "All
    0.06
    returns
    0.06
     One
    0.06
     approved
    0.06
    Five
    0.06
     Monitor
    0.06
     severely
    0.06
    Act Density 0.000%

    No Known Activations