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

    Neuronpedia

    INDEX
    Explanations

    viewing distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ゚
    0.73
    ز
    0.72
    Ꮩ
    0.71
    ג
    0.71
    ্ট
    0.71
    {}".
    0.66
    鏨
    0.66
    ह्
    0.65
    ગવાન
    0.65
     Bahkan
    0.65
    POSITIVE LOGITS
     nghiệm
    0.97
     وهذا
    0.88
     balik
    0.75
     alle
    0.75
    kter
    0.75
    也很
    0.75
     आपको
    0.74
     familien
    0.73
     बताता
    0.73
     నాలుగు
    0.72
    Act Density 0.001%

    No Known Activations