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

    Neuronpedia

    INDEX
    Explanations

    Arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cancer
    -0.07
    Rank
    -0.07
     pretext
    -0.07
     inaccur
    -0.06
    -et
    -0.06
    a
    -0.06
    line
    -0.06
     thứ
    -0.06
     Handling
    -0.06
     α
    -0.06
    POSITIVE LOGITS
     خدمت
    0.07
     эксплуата
    0.07
    营业
    0.07
    apellido
    0.06
     './../
    0.06
    �试
    0.06
    .awt
    0.06
     BIOS
    0.06
     生命周期函数
    0.06
    (newState
    0.06
    Act Density 0.020%

    No Known Activations