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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mills
    -0.07
     holders
    -0.06
     Drill
    -0.06
    ()).
    -0.06
    VOICE
    -0.06
     rigged
    -0.06
    靠
    -0.06
    /method
    -0.06
    Metadata
    -0.06
     türü
    -0.06
    POSITIVE LOGITS
     bachelor
    0.06
    ną
    0.06
     поба
    0.06
    满
    0.06
    ческий
    0.06
     veriyor
    0.06
     unh
    0.06
    approval
    0.06
     Exercise
    0.06
    Bitcoin
    0.06
    Act Density 0.004%

    No Known Activations