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

    Neuronpedia

    INDEX
    Explanations

    telling about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     दर्शाता
    0.41
     காட்சி
    0.39
    式
    0.37
     として
    0.36
    问道
    0.36
     Insertion
    0.36
    зад
    0.35
    ungkin
    0.35
    Insertion
    0.35
     Seriously
    0.35
    POSITIVE LOGITS
     about
    1.15
    about
    0.98
     عن
    0.91
     tentang
    0.86
     bahwa
    0.82
     về
    0.81
     apie
    0.74
     what
    0.73
     अबाउट
    0.73
     عنها
    0.73
    Act Density 0.027%

    No Known Activations