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

    Neuronpedia

    INDEX
    Explanations

    of from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billi
    -0.09
     rakyat
    -0.08
     intim
    -0.07
     Singer
    -0.07
    AVER
    -0.07
     FN
    -0.07
    	Big
    -0.07
    ostat
    -0.07
     sonuc
    -0.07
     среднем
    -0.07
    POSITIVE LOGITS
     contamination
    0.10
     undue
    0.09
    uben
    0.08
     contaminants
    0.08
     pollution
    0.08
     Ronald
    0.08
     interference
    0.08
     jargon
    0.07
    Errors
    0.07
     contradictions
    0.07
    Act Density 0.015%

    No Known Activations