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

    Neuronpedia

    INDEX
    Explanations

    desktop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Indianapolis
    -0.07
     Luo
    -0.07
     radial
    -0.07
     Adaptive
    -0.07
    -len
    -0.07
     Eur
    -0.07
    hub
    -0.06
     Julio
    -0.06
     timeStamp
    -0.06
     jdbc
    -0.06
    POSITIVE LOGITS
    ized
    0.07
    体现在
    0.07
    份
    0.07
    MC
    0.07
     meiden
    0.07
     yaptığı
    0.07
    周り
    0.06
     pisc
    0.06
    能得到
    0.06
    Combine
    0.06
    Act Density 0.095%

    No Known Activations