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

    Neuronpedia

    INDEX
    Explanations

    browser window

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vasena
    0.80
    ᆢ
    0.79
    <0xB3>
    0.76
     აღმასრულ
    0.74
    ⃣
    0.73
    <0xA4>
    0.73
    ătoare
    0.72
    ᓪ
    0.71
    𝑰
    0.71
     Aşağı
    0.71
    POSITIVE LOGITS
     размеров
    0.75
    reed
    0.73
     было
    0.72
    0.72
     первой
    0.70
     slits
    0.70
     съ
    0.70
    UTES
    0.70
     substitutes
    0.69
     doughnuts
    0.69
    Act Density 0.000%

    No Known Activations