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

    Neuronpedia

    INDEX
    Explanations

    rather than contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     customPlot
    0.32
    ังกฤษ
    0.29
    ട്ടുണ്ട്
    0.28
     SHALL
    0.25
     පු
    0.25
    线性
    0.25
     страда
    0.25
     YORK
    0.24
    റുണ്ട്
    0.24
    omorphisms
    0.24
    POSITIVE LOGITS
     rather
    0.92
    而不是
    0.89
    而非
    0.89
     instead
    0.87
    rather
    0.81
    instead
    0.79
     plutôt
    0.77
     вместо
    0.70
    Rather
    0.69
    ではなく
    0.68
    Act Density 0.623%

    No Known Activations