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

    Neuronpedia

    INDEX
    Explanations

    guided walking tours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Experiments
    0.40
     polarity
    0.40
    Simulation
    0.39
    тету
    0.39
     display
    0.39
    ochastic
    0.38
    Display
    0.38
     മാസ
    0.38
    Monitor
    0.38
     logarithm
    0.37
    POSITIVE LOGITS
     tours
    1.19
     tour
    1.17
     Tours
    1.09
    ツアー
    0.97
    Tour
    0.96
     Tour
    0.95
    tour
    0.89
     टूर
    0.87
    讲解
    0.81
    TOUR
    0.80
    Act Density 0.010%

    No Known Activations