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

    Neuronpedia

    INDEX
    Explanations

    News articles/stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    energy
    -0.07
    _algo
    -0.07
     Weapons
    -0.07
     Servers
    -0.06
     Threat
    -0.06
     Errors
    -0.06
     Game
    -0.06
    Either
    -0.06
    Often
    -0.06
     SAR
    -0.06
    POSITIVE LOGITS
    ์)
    0.06
    :::::::::::::
    0.06
    พระ
    0.06
    เภท
    0.06
    chooser
    0.06
    .setHorizontal
    0.06
    는지
    0.06
    Incre
    0.06
    |:
    0.06
    wid
    0.06
    Act Density 0.555%

    No Known Activations