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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Willie
    -0.07
    CD
    -0.06
    conciliation
    -0.06
    .Where
    -0.06
    ौड
    -0.06
    ?).
    -0.06
    Coupon
    -0.06
    ILED
    -0.06
     prospect
    -0.06
    -storage
    -0.06
    POSITIVE LOGITS
    .Ref
    0.07
    ----------↵↵
    0.07
    REF
    0.07
     refinery
    0.07
     refin
    0.07
     Ref
    0.06
    ΗΜΑ
    0.06
     Shak
    0.06
     Ngh
    0.06
    	Schema
    0.06
    Act Density 0.044%

    No Known Activations