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

    Neuronpedia

    INDEX
    Explanations

    single-digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (second
    -0.07
    镋
    -0.07
    _setting
    -0.07
    RING
    -0.07
     detecting
    -0.07
     HASH
    -0.06
    !(↵
    -0.06
    为主题的
    -0.06
     InputStream
    -0.06
    etch
    -0.06
    POSITIVE LOGITS
     tyranny
    0.07
    ceased
    0.07
     ovar
    0.07
    celand
    0.07
    קיים
    0.07
     algumas
    0.07
    Bus
    0.06
    굶
    0.06
    ennon
    0.06
    edores
    0.06
    Act Density 0.019%

    No Known Activations