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

    Neuronpedia

    INDEX
    Explanations

    outer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    冈
    -0.08
    _UPDATE
    -0.07
    �
    -0.07
     Responsibility
    -0.07
    Shock
    -0.07
     paycheck
    -0.07
    Dan
    -0.07
    _CITY
    -0.07
    altimore
    -0.07
    청
    -0.07
    POSITIVE LOGITS
     coli
    0.07
    .gz
    0.07
    𝔓
    0.07
     outer
    0.07
    gsub
    0.07
    .Rendering
    0.06
    ulis
    0.06
     déco
    0.06
     Outer
    0.06
    🔓
    0.06
    Act Density 0.004%

    No Known Activations