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

    Neuronpedia

    INDEX
    Explanations

    surfacing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चेंज
    0.48
     nombre
    0.45
    Ges
    0.44
     cambiado
    0.43
    çons
    0.42
     思っ
    0.42
    ábor
    0.41
    вания
    0.41
    ंशिक
    0.41
    Philip
    0.41
    POSITIVE LOGITS
     oub
    0.45
     CABINET
    0.44
     आँ
    0.41
     eyel
    0.40
     average
    0.40
     AVERAGE
    0.40
     obedience
    0.38
     advances
    0.38
     they
    0.38
     }^{\
    0.38
    Act Density 0.003%

    No Known Activations