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

    Neuronpedia

    INDEX
    Explanations

    oc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     controller
    -0.06
    Found
    -0.06
     exponent
    -0.06
    (menu
    -0.06
    _interaction
    -0.06
    Trong
    -0.06
    (cart
    -0.06
    consum
    -0.06
    Finished
    -0.06
     chancellor
    -0.06
    POSITIVE LOGITS
    ISH
    0.07
     tuo
    0.07
    รรม
    0.07
    갑
    0.07
     조사
    0.07
    okay
    0.06
    _PRO
    0.06
    _pdu
    0.06
     جهان
    0.06
    얼
    0.06
    Act Density 0.011%

    No Known Activations