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

    Neuronpedia

    INDEX
    Explanations

    programming-related code statements and syntax elements

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

    ; delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused41>
    -1.38
    <unused14>
    -1.38
    <unused28>
    -1.38
    <unused68>
    -1.38
    <unused74>
    -1.38
    <unused3>
    -1.38
    <unused17>
    -1.38
    <unused52>
    -1.38
    <unused79>
    -1.38
    <unused42>
    -1.38
    POSITIVE LOGITS
    ;
    0.85
     ;
    0.64
    );
    0.61
    ();
    0.60
    ';
    0.57
    };
    0.56
    ];
    0.56
    .;
    0.52
    ;
    0.52
    .
    0.52
    Act Density 0.026%

    No Known Activations