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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disse
    -0.06
    tails
    -0.06
    ises
    -0.06
     hei
    -0.06
    .exception
    -0.06
    {j
    -0.06
    _speed
    -0.06
     sugar
    -0.06
    185
    -0.06
    .name
    -0.06
    POSITIVE LOGITS
    liğin
    0.07
     än
    0.07
    _fname
    0.06
    ımızın
    0.06
     lez
    0.06
     scar
    0.06
    醫
    0.06
     شاهد
    0.06
    'nda
    0.06
    рут
    0.06
    Act Density 0.056%

    No Known Activations