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

    Neuronpedia

    INDEX
    Explanations

    physical phenomena

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्वय
    -0.07
     usernames
    -0.07
     TEX
    -0.07
    cookies
    -0.06
    746
    -0.06
    errs
    -0.06
    WebResponse
    -0.06
    _ind
    -0.06
    _COMP
    -0.06
     gebruik
    -0.06
    POSITIVE LOGITS
    ращ
    0.07
    sei
    0.06
     lam
    0.06
     Tomas
    0.06
     Yunan
    0.06
    迎
    0.06
     mop
    0.06
    мещ
    0.06
     JIT
    0.06
     facile
    0.06
    Act Density 0.031%

    No Known Activations