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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不斷
    -0.08
    coords
    -0.07
    index
    -0.07
    configure
    -0.07
    มา
    -0.06
    charge
    -0.06
    หาก
    -0.06
     inplace
    -0.06
     "")↵
    -0.06
    ﮪ
    -0.06
    POSITIVE LOGITS
    .overflow
    0.07
    堞
    0.07
     spoiled
    0.07
    _TRIANGLE
    0.07
     secrecy
    0.07
    锘
    0.07
    ﯝ
    0.07
     bomber
    0.07
    .isDefined
    0.07
     seaw
    0.07
    Act Density 0.076%

    No Known Activations