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

    Neuronpedia

    INDEX
    Explanations

    moderate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adviser
    -0.07
    achine
    -0.06
    जब
    -0.06
    ":[-
    -0.06
     Chairs
    -0.06
    rowth
    -0.06
    安全
    -0.06
     searches
    -0.06
     Brandon
    -0.06
    _radius
    -0.06
    POSITIVE LOGITS
    ISTR
    0.07
    کت
    0.07
     ud
    0.06
     З
    0.06
     التش
    0.06
    óz
    0.06
    ุย
    0.06
     plumbing
    0.06
     کمی
    0.06
     pist
    0.06
    Act Density 0.009%

    No Known Activations