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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xp
    -0.06
    ken
    -0.06
    ระบบ
    -0.06
     adaptable
    -0.06
     гра
    -0.06
     Lord
    -0.06
     statutes
    -0.06
    WithEmail
    -0.06
    ствен
    -0.06
     elephants
    -0.06
    POSITIVE LOGITS
     ampl
    0.07
     ukáz
    0.07
    _date
    0.06
     ray
    0.06
     Pří
    0.06
    泡
    0.06
    拒
    0.06
    /node
    0.06
     statistical
    0.06
     Canton
    0.06
    Act Density 0.031%

    No Known Activations