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

    Neuronpedia

    INDEX
    Explanations

    Google Analytics and web tracking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boone
    -0.07
    InOut
    -0.07
     automated
    -0.06
    .Clock
    -0.06
    .Format
    -0.06
     emailed
    -0.06
     Heaven
    -0.06
    _date
    -0.06
     预
    -0.06
    /foo
    -0.06
    POSITIVE LOGITS
     obrig
    0.07
     incontri
    0.07
    ความร
    0.06
     shack
    0.06
     �
    0.06
     pers
    0.06
    ardu
    0.06
     youthful
    0.06
     ['$
    0.06
    lerimiz
    0.06
    Act Density 0.010%

    No Known Activations