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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sink
    -0.06
     thoát
    -0.06
     baggage
    -0.06
     し
    -0.06
    setFont
    -0.06
     bitk
    -0.06
    -security
    -0.06
    Intel
    -0.06
     fog
    -0.06
    ченко
    -0.06
    POSITIVE LOGITS
     CEL
    0.07
     Mustang
    0.06
     amour
    0.06
     ô
    0.06
     UL
    0.06
    (comb
    0.06
     altru
    0.06
     COMPUTER
    0.06
     �
    0.06
    estli
    0.06
    Act Density 0.003%

    No Known Activations