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

    Neuronpedia

    INDEX
    Explanations

    renderer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تن
    -0.07
     delete
    -0.07
     stumbled
    -0.07
     pitched
    -0.07
    赣
    -0.06
     sweet
    -0.06
     maxx
    -0.06
    挞
    -0.06
     reads
    -0.06
     shootout
    -0.06
    POSITIVE LOGITS
    援助
    0.07
    _art
    0.07
    售后服务
    0.07
    ayaran
    0.07
    arkan
    0.07
    ournal
    0.07
    readystatechange
    0.07
    epar
    0.07
    רו
    0.06
    ={`
    0.06
    Act Density 0.002%

    No Known Activations