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

    Neuronpedia

    INDEX
    Explanations

    generating stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .↵↵
    -0.07
     personal
    -0.07
    ail
    -0.07
    onos
    -0.07
    personal
    -0.07
    个人
    -0.07
    UN
    -0.07
    ాడ
    -0.07
     llamada
    -0.07
    QT
    -0.07
    POSITIVE LOGITS
     zonder
    0.13
     बिना
    0.13
     WITHOUT
    0.13
     uitsluitend
    0.12
     בלי
    0.12
     ausschließlich
    0.12
     исключительно
    0.12
     lediglich
    0.11
     exclusivement
    0.11
     tanpa
    0.11
    Act Density 0.048%

    No Known Activations