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

    Neuronpedia

    INDEX
    Explanations

    structures or attributes related to data serialization or format specification

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

    Hexadecimal strings following a hyphen

    np_acts-logits-general · gemini-2.0-flash

    GUIDs and timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ་་
    -0.84
     $_"
    -0.83
     "\<
    -0.83
     iſt
    -0.82
     Anſ
    -0.82
     $_(
    -0.81
    SourceChecksum
    -0.80
    eſt
    -0.79
    NUMX
    -0.77
     Monfieur
    -0.76
    POSITIVE LOGITS
    ↵
    1.15
    ↵↵
    1.07
    );
    1.02
    )
    1.01
    ;
    1.01
    ),
    0.98
    ↵↵↵↵
    0.84
    ).
    0.84
    ];
    0.84
    ):
    0.84
    Act Density 4.537%

    No Known Activations