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

    Neuronpedia

    INDEX
    Explanations

    conversational exchanges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tennessee
    -0.07
     gö
    -0.07
    、や
    -0.06
     Harrison
    -0.06
     +#+#+#+#+#+
    -0.06
    à
    -0.06
    Õ
    -0.06
     AssemblyTrademark
    -0.06
     Minnesota
    -0.06
    ǐ
    -0.06
    POSITIVE LOGITS
    _lang
    0.07
     entsprech
    0.06
     часа
    0.06
    _control
    0.06
     sidewalk
    0.06
    conduct
    0.06
    Blocked
    0.06
    Sept
    0.06
     ✔
    0.06
     تغ
    0.06
    Act Density 0.066%

    No Known Activations