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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .registration
    -0.07
    グ
    -0.07
     adopted
    -0.07
    atı
    -0.07
     relacion
    -0.06
     provisioning
    -0.06
     wich
    -0.06
     полі
    -0.06
    culate
    -0.06
     Dann
    -0.06
    POSITIVE LOGITS
    columnName
    0.06
    jejer
    0.06
    .white
    0.06
    oods
    0.06
     Expect
    0.06
     بیرون
    0.06
    ulously
    0.06
    _timeline
    0.06
     يك
    0.06
     INA
    0.06
    Act Density 0.131%

    No Known Activations