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
    Jew
    0.39
     bermain
    0.38
     liquors
    0.37
    Mild
    0.37
    ၉
    0.37
    丶
    0.36
    瞄
    0.36
     secretions
    0.35
    ఫో
    0.35
    螯
    0.35
    POSITIVE LOGITS
     PHP
    0.70
     JavaScript
    0.66
     Java
    0.63
     django
    0.62
    PHP
    0.61
     javascript
    0.61
     Javascript
    0.61
     php
    0.57
    django
    0.56
     Python
    0.56
    Act Density 0.149%

    No Known Activations