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

    Neuronpedia

    INDEX
    Explanations

    data retention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bounded
    -0.07
     slun
    -0.06
     drawback
    -0.06
     tema
    -0.06
    |{↵
    -0.06
    ५
    -0.06
    135
    -0.06
     realtime
    -0.06
     चक
    -0.06
     schwer
    -0.06
    POSITIVE LOGITS
     Nicar
    0.07
    _az
    0.07
     浙江
    0.07
    Body
    0.06
    .controller
    0.06
     كور
    0.06
     POSIX
    0.06
     sert
    0.06
    ات
    0.06
    dim
    0.06
    Act Density 0.028%

    No Known Activations