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

    Neuronpedia

    INDEX
    Explanations

    floating-point numbers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ட்டு
    0.62
    στηκε
    0.61
     Haller
    0.60
    ůli
    0.60
     Père
    0.60
    agment
    0.59
    종
    0.59
    筆
    0.59
     கிருஷ்
    0.58
    剧
    0.58
    POSITIVE LOGITS
     double
    4.14
    double
    3.84
     Double
    3.83
    Double
    3.68
     float
    3.25
    float
    3.24
     DOUBLE
    3.22
     doubles
    3.03
     Float
    3.02
    DOUBLE
    3.00
    Act Density 0.365%

    No Known Activations