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

    Neuronpedia

    INDEX
    Explanations

    HIV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAP
    -0.07
     weg
    -0.06
    uellement
    -0.06
    yslu
    -0.06
     einige
    -0.06
    umption
    -0.06
     Bern
    -0.06
     RTBU
    -0.06
     conspic
    -0.06
    	suite
    -0.06
    POSITIVE LOGITS
    odef
    0.09
     Advoc
    0.08
     Tweets
    0.08
    (actor
    0.08
    elle
    0.07
     denied
    0.07
    лев
    0.07
     CDC
    0.07
    DATED
    0.07
    -bind
    0.07
    Act Density 0.001%

    No Known Activations