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

    Neuronpedia

    INDEX
    Explanations

    IMDb titles and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Edinburgh
    0.42
     patties
    0.41
     magnetized
    0.41
    麸
    0.41
     currants
    0.39
     crews
    0.39
    title
    0.39
    министра
    0.39
    plin
    0.39
    캐
    0.39
    POSITIVE LOGITS
     uzak
    0.40
    ץ
    0.39
    Sab
    0.38
     মাওলানা
    0.37
    Hawaii
    0.37
     never
    0.36
    塾
    0.36
    ایش
    0.36
    abbam
    0.36
    Alabama
    0.36
    Act Density 0.000%

    No Known Activations