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

    Neuronpedia

    INDEX
    Explanations

    work emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ný
    -0.07
    username
    -0.06
     vou
    -0.06
    ’t
    -0.06
     данны
    -0.06
     Street
    -0.06
    捷
    -0.06
    startdate
    -0.06
    ’nde
    -0.06
     mData
    -0.06
    POSITIVE LOGITS
    ίζ
    0.07
     Öğren
    0.07
     Explosion
    0.07
     ศ
    0.07
    isinin
    0.07
     appreciation
    0.07
     Ti
    0.07
     Cena
    0.06
    itm
    0.06
     progen
    0.06
    Act Density 0.011%

    No Known Activations