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

    Neuronpedia

    INDEX
    Explanations

    wrong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atis
    -0.08
     hoạt
    -0.07
    decorate
    -0.07
     definit
    -0.07
     hvě
    -0.06
    reiben
    -0.06
    evice
    -0.06
    úb
    -0.06
    pras
    -0.06
     grading
    -0.06
    POSITIVE LOGITS
     al
    0.07
     rewarded
    0.06
     Liter
    0.06
     conducted
    0.06
    ClassNotFoundException
    0.06
     الأولى
    0.06
     разв
    0.06
    <Application
    0.06
     Від
    0.06
     comprising
    0.06
    Act Density 0.002%

    No Known Activations