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

    Neuronpedia

    INDEX
    Explanations

    * as if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    说是
    0.45
     resins
    0.45
     TESTS
    0.43
     resellers
    0.43
     rehearsals
    0.42
     Res
    0.42
    ථ
    0.42
     resuscitation
    0.42
     প্রেসক্লাবের
    0.42
     និង
    0.41
    POSITIVE LOGITS
    et
    0.45
    kos
    0.44
     wirst
    0.43
    spiration
    0.40
    terna
    0.40
    Govern
    0.39
    bo
    0.39
    estado
    0.39
    dependency
    0.39
    Hop
    0.39
    Act Density 0.005%

    No Known Activations