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

    Neuronpedia

    INDEX
    Explanations

    having

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    播
    -0.06
     legisl
    -0.06
    Models
    -0.06
    ‎
    -0.06
    Sales
    -0.06
     '.')
    -0.06
    cstring
    -0.06
     NAME
    -0.06
     Exclusive
    -0.06
     Replace
    -0.06
    POSITIVE LOGITS
     хотел
    0.07
     atención
    0.07
    zn
    0.07
     ».
    0.06
     역시
    0.06
    ヒ
    0.06
    риг
    0.06
     zahrani
    0.06
    BeenCalled
    0.06
     fotoğraf
    0.06
    Act Density 0.000%

    No Known Activations