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

    Neuronpedia

    INDEX
    Explanations

    say "per"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bestehen
    -0.08
    ERING
    -0.08
    LObject
    -0.08
    華
    -0.08
     steh
    -0.08
    ಿರಿ
    -0.07
     Прич
    -0.07
     Persistent
    -0.07
     FOUNDATION
    -0.07
     Crian
    -0.07
    POSITIVE LOGITS
     প্রতি
    0.13
     rate
    0.12
    _rate
    0.11
     प्रति
    0.11
    Rate
    0.11
    .rate
    0.11
    /hour
    0.11
     rates
    0.11
     schneller
    0.10
    -rate
    0.10
    Act Density 0.018%

    No Known Activations