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

    Neuronpedia

    INDEX
    Explanations

    commercial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Many
    -0.07
    	border
    -0.07
     dumb
    -0.06
     thrift
    -0.06
     suck
    -0.06
     Cic
    -0.06
    Motor
    -0.06
    Girls
    -0.06
     Angola
    -0.06
     agg
    -0.06
    POSITIVE LOGITS
    жу
    0.07
     Kanunu
    0.06
     dbc
    0.06
    ，其中
    0.06
    _spell
    0.06
    ように
    0.06
    .eps
    0.06
    zbek
    0.06
     Incredible
    0.06
     xo
    0.06
    Act Density 0.028%

    No Known Activations