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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invasive
    -0.07
     تاثیر
    -0.06
     defiance
    -0.06
     aument
    -0.06
     timely
    -0.06
     forme
    -0.06
     şekilde
    -0.06
     plais
    -0.06
     llama
    -0.06
    STDOUT
    -0.06
    POSITIVE LOGITS
     wie
    0.06
    -chart
    0.06
     journalistic
    0.06
    _GREEN
    0.06
     امتی
    0.06
    owied
    0.06
     UserData
    0.06
    -ln
    0.06
    nov
    0.06
    меть
    0.06
    Act Density 0.084%

    No Known Activations