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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrath
    -0.06
     tránh
    -0.06
     Tray
    -0.06
     deployment
    -0.06
     Xem
    -0.06
    ilk
    -0.06
     nurse
    -0.06
    recall
    -0.06
     claw
    -0.06
    (bp
    -0.06
    POSITIVE LOGITS
     =============================================================================↵
    0.07
    msgid
    0.07
     ]);↵↵
    0.07
    andex
    0.06
    _override
    0.06
     vowel
    0.06
    getSource
    0.06
    )^
    0.06
    ifold
    0.06
    가능
    0.06
    Act Density 0.070%

    No Known Activations