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

    Neuronpedia

    INDEX
    Explanations

    assigning zero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eleven
    0.85
     hùng
    0.82
     Fifteen
    0.81
    十九章
    0.80
    ੍ਰ
    0.79
    <unused227>
    0.79
     Fourteen
    0.78
    Eleven
    0.77
     Sixteen
    0.77
     Seventeen
    0.76
    POSITIVE LOGITS
    0
    3.53
    ０
    2.99
     zero
    2.72
    ۰
    2.47
    ૦
    2.36
    ০
    2.35
     ০
    2.33
     Zero
    2.32
    ٠
    2.30
    ०
    2.29
    Act Density 0.996%

    No Known Activations