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

    Neuronpedia

    INDEX
    Explanations

    programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ndi
    0.83
    ená
    0.70
    ίνη
    0.68
    Whitney
    0.66
     الاتحاد
    0.66
    ॉड
    0.65
     यांचा
    0.65
    nop
    0.64
    放心
    0.63
     própria
    0.63
    POSITIVE LOGITS
    py
    1.43
    java
    1.16
     java
    1.12
    cpp
    1.10
     py
    1.03
    PY
    1.00
     python
    0.97
    JAVA
    0.96
     js
    0.95
     cpp
    0.94
    Act Density 0.074%

    No Known Activations