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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bieber
    -0.07
    Footer
    -0.06
    Certainly
    -0.06
     Код
    -0.06
    FG
    -0.06
    exception
    -0.06
     retrospective
    -0.06
     生命周期
    -0.06
     Several
    -0.06
    ु�
    -0.06
    POSITIVE LOGITS
     scalp
    0.07
    elige
    0.07
    ны
    0.07
     kvinnor
    0.06
    査
    0.06
     möchten
    0.06
    _company
    0.06
    шили
    0.06
    ерп
    0.06
    编
    0.06
    Act Density 0.094%

    No Known Activations