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

    Neuronpedia

    INDEX
    Explanations

    instances of the PHP superglobal variable $_

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

    accessing $_POST and $_SESSION

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Juego
    -0.41
    发表于
    -0.41
     död
    -0.40
     justifyContent
    -0.39
     stället
    -0.39
     Kombination
    -0.39
     garantizar
    -0.38
    xtext
    -0.38
     yanı
    -0.38
    ungkinkan
    -0.38
    POSITIVE LOGITS
     $_
    2.34
    $_
    1.58
    ($_
    1.55
    =$_
    1.35
     ($_
    1.34
    ,$_
    1.34
    )$_
    1.32
    ".$_
    1.25
    .$_
    1.19
    "$_
    0.98
    Act Density 0.004%

    No Known Activations