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

    Neuronpedia

    INDEX
    Explanations

    object properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وح
    0.45
    arjo
    0.43
    খর
    0.40
     pagamento
    0.39
    运营
    0.38
     ಕೇಂದ್ರ
    0.38
     सेंटर
    0.38
     Ipsum
    0.38
     latitudine
    0.38
     condiciones
    0.38
    POSITIVE LOGITS
     property
    1.55
    Property
    1.34
    property
    1.34
     Property
    1.31
     PROPERTY
    1.13
     properties
    1.10
     propriété
    1.10
     propiedad
    1.02
     proprietà
    1.02
    PROPERTY
    1.01
    Act Density 0.018%

    No Known Activations