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

    Neuronpedia

    INDEX
    Explanations

    function calls and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wetlands
    0.50
     historischen
    0.48
    癃
    0.47
    溼
    0.46
    筏
    0.46
     Dermatology
    0.46
    餾
    0.46
     veineux
    0.45
     অক্সিজ
    0.45
    橡胶
    0.44
    POSITIVE LOGITS
    android
    0.46
    function
    0.44
     b
    0.44
    1
    0.44
    Z
    0.43
    Android
    0.43
    5
    0.43
     Android
    0.43
     function
    0.43
    c
    0.43
    Act Density 0.004%

    No Known Activations