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

    Neuronpedia

    INDEX
    Explanations

    this was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ABOR
    0.39
     গণতান্ত্রিক
    0.38
     Freddy
    0.37
     Democratic
    0.37
     encuentran
    0.37
     legislación
    0.37
     Locomotive
    0.36
     encuentre
    0.36
    嫋
    0.36
     Reactors
    0.36
    POSITIVE LOGITS
     Whose
    0.48
     whose
    0.47
    roads
    0.45
    whose
    0.45
    Walk
    0.43
    Road
    0.42
    সন
    0.41
     WALK
    0.41
     Roads
    0.41
     roads
    0.40
    Act Density 0.000%

    No Known Activations