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

    Neuronpedia

    INDEX
    Explanations

    programming keywords

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cout
    0.87
    vector
    0.86
     string
    0.85
    string
    0.85
     vector
    0.84
     cout
    0.73
    algorithm
    0.73
     különböz
    0.72
     পাকিস্তানকে
    0.70
    暂时
    0.69
    POSITIVE LOGITS
     const
    2.05
    const
    1.95
     std
    1.82
    std
    1.81
    reinterpret
    1.20
     Const
    1.13
    Const
    1.10
     constriction
    1.03
    Standard
    0.97
     standard
    0.95
    Act Density 0.219%

    No Known Activations