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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ृत
    -0.07
     aware
    -0.07
    ﾊ
    -0.06
     ue
    -0.06
     numberOfRows
    -0.06
     человечес
    -0.06
     LED
    -0.06
    ره
    -0.06
     olmaktadır
    -0.06
     Пот
    -0.06
    POSITIVE LOGITS
    _estado
    0.07
    %)
    0.07
     disruptions
    0.07
    _fds
    0.07
    amina
    0.07
    _fill
    0.06
     freel
    0.06
    _plural
    0.06
    )>>
    0.06
     recommendation
    0.06
    Act Density 0.002%

    No Known Activations