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

    Neuronpedia

    INDEX
    Explanations

    Fulfillment, revolution, contribute, weekend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >,
    0.50
    ;
    0.50
     (
    0.50
                
    0.48
    },
    0.47
     as
    0.47
    ),
    0.47
     berths
    0.46
    >
    0.46
     atau
    0.45
    POSITIVE LOGITS
     Fisch
    0.48
     Reinhold
    0.46
     religiosos
    0.44
    hkar
    0.43
     zij
    0.42
    zgl
    0.42
    ICH
    0.42
    kmeans
    0.42
    layered
    0.41
    ramethyl
    0.41
    Act Density 0.000%

    No Known Activations