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

    Neuronpedia

    INDEX
    Explanations

    360

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !(
    -0.08
     дод
    -0.07
    анных
    -0.07
    (N
    -0.07
    ету
    -0.07
    (p
    -0.07
    ,msg
    -0.07
    �试
    -0.07
     Kč
    -0.06
     emb
    -0.06
    POSITIVE LOGITS
     Gujar
    0.07
     diyor
    0.06
     implicit
    0.06
    components
    0.06
    ה
    0.06
     barracks
    0.05
     microscope
    0.05
    اسة
    0.05
    urator
    0.05
     Kerr
    0.05
    Act Density 0.005%

    No Known Activations