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

    Neuronpedia

    INDEX
    Explanations

    creating copies of data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CLICK
    0.44
    USTR
    0.42
    “
    0.42
    ­
    0.41
    constit
    0.40
    CLICK
    0.40
    PICK
    0.40
    臨床
    0.38
     indicada
    0.38
     નક્કી
    0.38
    POSITIVE LOGITS
     사용하여
    0.47
    NetStandard
    0.46
     খাঁর
    0.46
    ື້ນ
    0.45
     ของ
    0.45
    Improved
    0.44
    шает
    0.44
     तैर
    0.44
     ใช้
    0.43
    渍
    0.43
    Act Density 0.001%

    No Known Activations