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

    Neuronpedia

    INDEX
    Explanations

    stages and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     after
    1.25
     After
    1.21
     לאחר
    1.14
     setelah
    1.12
     после
    1.12
     Setelah
    1.11
    after
    1.10
     dopo
    1.08
     după
    1.07
     após
    1.05
    POSITIVE LOGITS
     مباشرة
    0.91
     onwards
    0.85
     مباش
    0.85
    BleStatus
    0.80
    才是
    0.76
    लोड
    0.73
     disappears
    0.70
     disappear
    0.70
    失效
    0.70
    hood
    0.69
    Act Density 0.174%

    No Known Activations