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

    Neuronpedia

    INDEX
    Explanations

    supersymmetry breaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ジョ
    -0.07
    _threads
    -0.07
    _fraction
    -0.06
    .Utils
    -0.06
     обуч
    -0.06
     Jays
    -0.06
    ния
    -0.06
    Blocking
    -0.06
    _flush
    -0.06
    _CONFIGURATION
    -0.06
    POSITIVE LOGITS
     Ads
    0.07
    _offer
    0.06
    }`);↵↵
    0.06
    .ai
    0.06
    :g
    0.06
     [--
    0.06
     humanities
    0.06
    NavLink
    0.06
    <r
    0.06
    除
    0.06
    Act Density 0.003%

    No Known Activations