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

    Neuronpedia

    INDEX
    Explanations

    NOT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leadership
    -0.07
    .,
    -0.07
    优势
    -0.07
     Leadership
    -0.07
    -vector
    -0.06
    σιο
    -0.06
    .dds
    -0.06
     counter
    -0.06
     ]}↵
    -0.06
     plaintiffs
    -0.06
    POSITIVE LOGITS
    ("!
    0.06
    .rot
    0.06
     tiết
    0.06
    Fund
    0.06
     Počet
    0.06
     overlooked
    0.06
     fal
    0.06
    483
    0.06
    /de
    0.06
    _FETCH
    0.06
    Act Density 0.002%

    No Known Activations