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

    Neuronpedia

    INDEX
    Explanations

    scientific/mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     words
    -0.06
     marketed
    -0.06
     marching
    -0.06
    inning
    -0.06
     nich
    -0.06
    redit
    -0.06
     capabilities
    -0.06
    ầm
    -0.06
    gram
    -0.06
     発
    -0.06
    POSITIVE LOGITS
    >Edit
    0.07
    menuItem
    0.07
    )<=
    0.07
    щина
    0.07
     yöntem
    0.07
    avou
    0.06
    ],↵↵
    0.06
    )object
    0.06
     ])↵↵
    0.06
     Regulatory
    0.06
    Act Density 0.065%

    No Known Activations