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

    Neuronpedia

    INDEX
    Explanations

    Big

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tensions
    -0.07
    ках
    -0.07
     přen
    -0.07
    xbf
    -0.07
     ergonomic
    -0.06
    hits
    -0.06
     갈
    -0.06
    shouldBe
    -0.06
    exc
    -0.06
    ToJson
    -0.06
    POSITIVE LOGITS
    .Persistence
    0.07
    /code
    0.06
     QDialog
    0.06
    /tr
    0.06
    	line
    0.06
    report
    0.06
     loại
    0.06
     doprav
    0.05
    ig
    0.05
    _commit
    0.05
    Act Density 0.000%

    No Known Activations