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

    Neuronpedia

    INDEX
    Explanations

    numbers in URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ፤
    0.80
    ropy
    0.79
    ஃ
    0.74
    ↻
    0.71
    ";
    0.71
    MappingURL
    0.70
    Hozzáférés
    0.68
     sanity
    0.68
    saturation
    0.67
    optimize
    0.67
    POSITIVE LOGITS
    2.08
     ৪
    1.15
     ६
    1.05
    6
    1.05
     ८
    1.05
     ३
    1.04
    7
    1.02
     ४
    1.02
    8
    0.99
     २
    0.99
    Act Density 0.012%

    No Known Activations