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

    Neuronpedia

    INDEX
    Explanations

    su

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oints
    -0.07
     wel
    -0.07
    coding
    -0.06
    		↵		↵
    -0.06
    _since
    -0.06
    ैस
    -0.06
     Rising
    -0.06
     wszyst
    -0.06
    meyi
    -0.06
     layoffs
    -0.06
    POSITIVE LOGITS
    .Res
    0.07
    urv
    0.07
     lob
    0.07
    apphire
    0.07
     Guinea
    0.06
     --->
    0.06
     shredd
    0.06
     kural
    0.06
     или
    0.06
    	sl
    0.06
    Act Density 0.068%

    No Known Activations