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

    Neuronpedia

    INDEX
    Explanations

    PHP code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Luther
    0.39
    Coal
    0.38
    elij
    0.38
    த்தோ
    0.38
    PSI
    0.38
    ESG
    0.38
     ESG
    0.37
    睑
    0.37
     Coal
    0.37
     PSL
    0.37
    POSITIVE LOGITS
    <?
    0.88
     <?
    0.87
     php
    0.85
     <?=
    0.82
     PHP
    0.78
    "><?
    0.77
     ?>
    0.75
    <?=
    0.75
    ><?
    0.75
    php
    0.75
    Act Density 0.008%

    No Known Activations