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

    Neuronpedia

    INDEX
    Explanations

    upport

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SWT
    -0.07
     Toll
    -0.07
    .sul
    -0.06
    stre
    -0.06
     Gun
    -0.06
     stub
    -0.06
     Sell
    -0.06
    xor
    -0.06
     значительно
    -0.06
     pestic
    -0.06
    POSITIVE LOGITS
     literary
    0.08
    .Cookies
    0.06
    (yy
    0.06
    (ml
    0.06
    UpInside
    0.06
     casually
    0.06
    .factor
    0.06
     adjud
    0.06
    ,file
    0.06
     hurd
    0.06
    Act Density 0.000%

    No Known Activations