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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    597
    -0.07
     Ghost
    -0.07
     çıkar
    -0.07
    asthan
    -0.06
    σα
    -0.06
     offenses
    -0.06
     mole
    -0.06
     ble
    -0.06
     raft
    -0.06
     mustard
    -0.06
    POSITIVE LOGITS
    ";}↵
    0.07
    ';
    0.06
    ész
    0.06
     wakeup
    0.06
    แนะนำ
    0.06
    ワイト
    0.06
    ensely
    0.06
    for
    0.06
    şk
    0.06
    didn
    0.06
    Act Density 0.046%

    No Known Activations