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

    Neuronpedia

    INDEX
    Explanations

    Go

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _orig
    -0.07
    DataManager
    -0.07
    NSAttributedString
    -0.06
    _recent
    -0.06
     buses
    -0.06
    umeric
    -0.06
     -*-↵
    -0.06
     farming
    -0.06
     isset
    -0.06
     ropes
    -0.06
    POSITIVE LOGITS
    Least
    0.07
     up
    0.07
    going
    0.06
     caract
    0.06
     SYN
    0.06
    specific
    0.06
    ‌ی
    0.06
     evade
    0.06
    (MethodImplOptions
    0.06
     HEAD
    0.06
    Act Density 0.004%

    No Known Activations