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

    Neuronpedia

    INDEX
    Explanations

    keywords and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cidas
    0.67
     Kuz
    0.65
    ुरू
    0.64
     έως
    0.62
     Mom
    0.61
    铱
    0.59
    こうした
    0.59
     Kus
    0.59
     mieszkań
    0.58
    usti
    0.58
    POSITIVE LOGITS
     thereon
    0.75
    Handler
    0.74
    共に
    0.74
    点评
    0.73
    Plate
    0.72
     therefrom
    0.72
    Bridge
    0.71
     Bridges
    0.70
     equals
    0.69
    ("");
    0.68
    Act Density 1.609%

    No Known Activations