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

    Neuronpedia

    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ва
    -0.07
    -0.07
    以为
    -0.06
     늘
    -0.06
    position
    -0.06
    arges
    -0.06
    <footer
    -0.06
    super
    -0.06
    )?.
    -0.06
     sửa
    -0.06
    POSITIVE LOGITS
     OPER
    0.07
     ukaz
    0.07
    onus
    0.07
    �인
    0.07
     stringBy
    0.07
    ิงห
    0.06
     參
    0.06
    中に
    0.06
     heiß
    0.06
    (Id
    0.06
    Act Density 0.007%

    No Known Activations