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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tbl
    -0.07
     brigade
    -0.07
    	channel
    -0.06
     irrig
    -0.06
    .extra
    -0.06
     захисту
    -0.06
     Zhang
    -0.06
    .ge
    -0.06
    DataTask
    -0.06
     Rak
    -0.06
    POSITIVE LOGITS
    estimated
    0.06
    represented
    0.06
    ClassNotFoundException
    0.06
     por
    0.06
    کات
    0.06
     Attempt
    0.06
     погод
    0.06
    uellement
    0.05
     กรก
    0.05
    ้ม
    0.05
    Act Density 0.000%

    No Known Activations