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

    Neuronpedia

    INDEX
    Explanations

    numbers and math

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁤
    0.49
     reiter
    0.47
    0.47
     ETL
    0.46
    ​—
    0.46
     Hasbro
    0.46
    0.45
    <unused7>
    0.45
     Cortana
    0.45
    0.45
    POSITIVE LOGITS
     由于
    0.37
    It
    0.37
    If
    0.36
    由于
    0.34
    От
    0.34
    巳
    0.34
     السالب
    0.33
    He
    0.33
    Here
    0.33
    nil
    0.33
    Act Density 0.441%

    No Known Activations