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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hus
    -0.07
    оят
    -0.07
    .gl
    -0.06
    Crop
    -0.06
    енность
    -0.06
    존
    -0.06
    yscale
    -0.06
     begs
    -0.06
    ยา
    -0.06
    ither
    -0.06
    POSITIVE LOGITS
     часть
    0.07
    ите
    0.07
    开始
    0.07
     свій
    0.07
     LIS
    0.06
    ernen
    0.06
    /std
    0.06
     setSelected
    0.06
     stormed
    0.06
    rr
    0.06
    Act Density 0.040%

    No Known Activations