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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thiết
    -0.07
     �
    -0.07
     skillet
    -0.07
    䲢
    -0.07
    📢
    -0.07
     quanto
    -0.07
     headlines
    -0.07
     металл
    -0.06
     Suffolk
    -0.06
     Illum
    -0.06
    POSITIVE LOGITS
    uhe
    0.07
     running
    0.07
    outing
    0.07
     WA
    0.07
    READING
    0.07
    解放
    0.06
    .calendar
    0.06
    	the
    0.06
    olo
    0.06
     pass
    0.06
    Act Density 0.001%

    No Known Activations