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
     Alf
    -0.07
     helt
    -0.06
     hấp
    -0.06
     محل
    -0.06
    _MAT
    -0.06
     ms
    -0.06
     entries
    -0.06
    support
    -0.06
    ifying
    -0.06
     incorporation
    -0.06
    POSITIVE LOGITS
    -duty
    0.07
    	order
    0.06
     Governance
    0.06
    iền
    0.06
    Order
    0.06
    -display
    0.06
     krij
    0.06
    ;%
    0.06
    olist
    0.06
    >tagger
    0.06
    Act Density 0.004%

    No Known Activations