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

    Neuronpedia

    INDEX
    Explanations

    controller and Functional Safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िकल
    0.38
     தலைமையில்
    0.38
     ครั้ง
    0.37
     लग्न
    0.37
     filtered
    0.36
    ించండి
    0.36
     optimised
    0.36
    蝼
    0.35
     compute
    0.35
    ించిన
    0.35
    POSITIVE LOGITS
    tuk
    0.44
    潑
    0.40
    ESPN
    0.39
    tut
    0.39
    Et
    0.38
    Euro
    0.38
    proof
    0.37
    prove
    0.37
    ኽ
    0.37
    atmosphere
    0.37
    Act Density 0.001%

    No Known Activations