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

    Neuronpedia

    INDEX
    Explanations

    python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x86>
    0.61
     Pamplona
    0.59
     painted
    0.58
    elbe
    0.58
    lice
    0.58
    lays
    0.56
     във
    0.56
     conflictos
    0.55
    lte
    0.55
    ed
    0.55
    POSITIVE LOGITS
    Python
    0.82
    د
    0.79
    JavaScript
    0.71
     Python
    0.66
    مر
    0.62
     JavaScript
    0.61
    מש
    0.59
     python
    0.58
    src
    0.55
    import
    0.55
    Act Density 1.152%

    No Known Activations