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

    Neuronpedia

    INDEX
    Explanations

    rub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mirror
    -0.07
    :mm
    -0.07
     Abbey
    -0.06
     Zoo
    -0.06
     hide
    -0.06
    VIEW
    -0.06
     Viv
    -0.06
    .period
    -0.06
    OCK
    -0.06
    enie
    -0.06
    POSITIVE LOGITS
     Cbd
    0.07
     rubbed
    0.07
    บาคาร
    0.07
     ?>><?
    0.07
    ...',
    0.07
    ஹ
    0.07
    _recipe
    0.07
     Đặc
    0.07
     가장
    0.07
    巡回
    0.07
    Act Density 0.008%

    No Known Activations