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

    Neuronpedia

    INDEX
    Explanations

    optional parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    തമായ
    0.42
    тили
    0.41
    +:
    0.41
    ಃ
    0.40
     없고
    0.38
    μου
    0.38
     STILL
    0.38
    리그
    0.38
    +\
    0.37
     спорта
    0.37
    POSITIVE LOGITS
     optional
    1.05
    optional
    1.03
     Optional
    1.00
    Optional
    0.98
    可选
    0.79
    OPT
    0.70
    Optionals
    0.69
     optionally
    0.58
     opt
    0.57
     elective
    0.53
    Act Density 0.013%

    No Known Activations