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

    Neuronpedia

    INDEX
    Explanations

    SQL query results in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PHP
    0.50
     PHP
    0.48
     Illuminate
    0.47
     php
    0.47
    eseorang
    0.46
    Illuminate
    0.46
    hydrate
    0.45
    Php
    0.45
     ($_
    0.45
    OrFail
    0.44
    POSITIVE LOGITS
    sq
    0.42
     Jio
    0.42
     ball
    0.40
     Mo
    0.40
     Karachi
    0.38
     Haw
    0.38
     FIR
    0.38
     goog
    0.37
    Mo
    0.37
    mv
    0.37
    Act Density 0.002%

    No Known Activations