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

    Neuronpedia

    INDEX
    Explanations

    plot descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Constit
    0.46
    Middleware
    0.43
    잊
    0.43
    隘
    0.42
    Trong
    0.41
    Internal
    0.41
    |\
    0.40
     DCHECK
    0.40
    それぞれ
    0.40
    Analysis
    0.40
    POSITIVE LOGITS
    inent
    0.47
     सेंटीमीटर
    0.43
    imeters
    0.43
    ভিল
    0.43
     vendedores
    0.43
    ický
    0.42
     industria
    0.42
     vente
    0.41
     Fiji
    0.41
     mailing
    0.41
    Act Density 0.003%

    No Known Activations