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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prostřed
    -0.07
     Puerto
    -0.07
     Voor
    -0.07
     Barbar
    -0.07
     Grammar
    -0.06
     recounted
    -0.06
     bathroom
    -0.06
     пош
    -0.06
     ของ
    -0.06
    кі
    -0.06
    POSITIVE LOGITS
    (curl
    0.07
    ラク
    0.06
    _DIAG
    0.06
     curl
    0.06
    wnd
    0.06
     progressDialog
    0.06
     awakening
    0.06
    edx
    0.06
     +
    0.06
    划
    0.06
    Act Density 0.067%

    No Known Activations