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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alliances
    -0.07
     percentages
    -0.07
     Nas
    -0.07
     obsess
    -0.06
    الا
    -0.06
    _'+
    -0.06
     bottoms
    -0.06
     '',
    -0.06
    깨
    -0.06
    (Android
    -0.06
    POSITIVE LOGITS
     새글
    0.07
     پس
    0.06
     ışık
    0.06
    @Inject
    0.06
    ervised
    0.06
    _SCHEMA
    0.06
    0.06
     vergi
    0.06
    hammer
    0.06
    提
    0.06
    Act Density 0.000%

    No Known Activations