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

    Neuronpedia

    INDEX
    Explanations

    automatic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haze
    -0.08
     aval
    -0.07
    状
    -0.07
     Magazin
    -0.07
     Magazine
    -0.07
    EL
    -0.07
     পরিস্থিত
    -0.07
    沙
    -0.07
     Lea
    -0.07
     היה
    -0.07
    POSITIVE LOGITS
     directo
    0.10
     مباشر
    0.09
    绑定
    0.08
     रे
    0.08
     прям
    0.08
     direkten
    0.08
     direkte
    0.08
     explíc
    0.08
     Motorsport
    0.08
    යෙන්
    0.08
    Act Density 0.003%

    No Known Activations