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

    Neuronpedia

    INDEX
    Explanations

    breakdown of X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),
    0.59
    ?
    0.58
    );
    0.58
    )
    0.53
    ;
    0.52
    ).
    0.52
    !
    0.52
    L
    0.51
     Overall
    0.51
    >
    0.49
    POSITIVE LOGITS
    iędzy
    0.52
    widgetTo
    0.52
    pares
    0.51
    ຂອງ
    0.51
    innerApiCalls
    0.50
     τησ
    0.50
     sAlarm
    0.49
    acido
    0.49
     odnos
    0.49
    ostiene
    0.49
    Act Density 2.315%

    No Known Activations