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

    Neuronpedia

    INDEX
    Explanations

    Changes and processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aims
    -0.07
     wm
    -0.06
     punish
    -0.06
     met
    -0.06
    contain
    -0.06
     favourites
    -0.06
     таком
    -0.06
    Labour
    -0.06
     ailments
    -0.06
    _comm
    -0.06
    POSITIVE LOGITS
     OCD
    0.06
    +"</
    0.06
    (++
    0.06
    @endsection
    0.06
    599
    0.06
    _optimizer
    0.06
     
    0.06
     favicon
    0.06
    /******/↵
    0.06
     foster
    0.06
    Act Density 0.299%

    No Known Activations