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

    Neuronpedia

    INDEX
    Explanations

    the use of the underscore with variable names in PHP

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    php superglobals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $}}
    -0.40
    awtextra
    -0.40
    })}
    -0.39
    })}\
    -0.38
     Anfitrión
    -0.36
    TagMode
    -0.36
    ])));
    -0.35
    ]))
    -0.34
    ایج
    -0.33
    ))));
    -0.33
    POSITIVE LOGITS
    ($_
    0.93
     المعيارى
    0.62
     $_(
    0.61
     zwiſchen
    0.60
     $_-
    0.60
    [@BOS@]
    0.58
    naeus
    0.58
    <unused41>
    0.57
    <unused28>
    0.57
    <unused14>
    0.57
    Act Density 0.001%

    No Known Activations