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

    Neuronpedia

    INDEX
    Explanations

    web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    䢺
    -0.07
    ishes
    -0.07
     atmos
    -0.07
    蹢
    -0.07
     MAS
    -0.07
    مف
    -0.06
    假冒
    -0.06
    独一无
    -0.06
     rope
    -0.06
    Keywords
    -0.06
    POSITIVE LOGITS
     بن
    0.08
     tend
    0.07
    /parser
    0.07
     Unexpected
    0.07
     усили
    0.07
     طويلة
    0.07
    .offsetWidth
    0.07
    UpDown
    0.07
     Policies
    0.07
    _precision
    0.07
    Act Density 0.288%

    No Known Activations