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

    Neuronpedia

    INDEX
    Explanations

    CORS Api Marty JSON YOLO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.70
    ת
    1.61
    т
    1.58
    ח
    1.54
    g
    1.50
     couches
    1.41
    𝘬
    1.39
    ול
    1.39
    䥑
    1.37
    า
    1.36
    POSITIVE LOGITS
    স্পতি
    1.35
    {
    1.31
    ść
    1.26
    ної
    1.23
    নি
    1.22
    ્સ
    1.19
    ्स
    1.19
    Aby
    1.17
    शीलता
    1.16
    ときの
    1.16
    Act Density 0.000%

    No Known Activations