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

    Neuronpedia

    INDEX
    Explanations

    steps and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    З
    0.59
    리
    0.57
    பெ
    0.50
    ？
    0.49
    《
    0.48
    公司
    0.47
    ᾷ
    0.47
    攻擊
    0.47
    webpack
    0.46
    {
    0.45
    POSITIVE LOGITS
    Circular
    0.50
     Constitución
    0.49
     Seiten
    0.47
     disappointment
    0.47
     Ansari
    0.46
     Constituição
    0.45
    <unused2122>
    0.45
     Н
    0.44
     Buckley
    0.44
    Indent
    0.43
    Act Density 0.112%

    No Known Activations