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

    Neuronpedia

    INDEX
    Explanations

    thespruce.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     @
    0.63
    anterior
    0.63
    <a>
    0.59
    @
    0.57
    Steam
    0.55
     রেজিস্ট
    0.53
    {-
    0.52
    Địa
    0.52
     <-
    0.52
    बच्च
    0.52
    POSITIVE LOGITS
     Bride
    0.98
    দ্বীপ
    0.88
    <unused328>
    0.87
    𝑠
    0.81
    undos
    0.79
    ಾನೂ
    0.79
     Clements
    0.79
     돼요
    0.78
     CLE
    0.77
    <unused2165>
    0.77
    Act Density 0.048%

    No Known Activations