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

    Neuronpedia

    INDEX
    Explanations

    valves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bits
    -0.07
    Leaders
    -0.07
    атів
    -0.07
    -al
    -0.06
     machine
    -0.06
    hangi
    -0.06
     безопасности
    -0.06
     ""↵
    -0.06
     injected
    -0.06
    <Project
    -0.06
    POSITIVE LOGITS
    ICLE
    0.07
    ][/
    0.07
     книж
    0.07
    erdem
    0.07
    rios
    0.06
    calculator
    0.06
     uniformly
    0.06
     مصر
    0.06
    /prom
    0.06
    itecture
    0.06
    Act Density 0.037%

    No Known Activations