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

    Neuronpedia

    INDEX
    Explanations

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.11
    ០
    1.04
    ००
    1.02
    ૦
    0.96
    𝟬
    0.96
    ੦
    0.95
    ೧
    0.95
    ۰۰
    0.92
    ០០
    0.92
    ০
    0.90
    POSITIVE LOGITS
    ⁹
    0.87
     ninety
    0.87
    कालय
    0.85
     за
    0.82
     също
    0.80
     nineties
    0.79
     też
    0.77
     Ninety
    0.77
    十八章
    0.76
    finalize
    0.76
    Act Density 0.335%

    No Known Activations