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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    жал
    -0.08
    不超过
    -0.07
    -grow
    -0.07
    _SRC
    -0.07
    受け
    -0.07
     Bel
    -0.06
    _ap
    -0.06
    .compat
    -0.06
    🦒
    -0.06
    🏘
    -0.06
    POSITIVE LOGITS
    Fizz
    0.07
     trafficking
    0.07
    �
    0.07
    恰当
    0.07
    甜
    0.07
    Correct
    0.07
     addictive
    0.07
    生产车间
    0.06
    heiten
    0.06
    وط
    0.06
    Act Density 0.058%

    No Known Activations