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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SharedPreferences
    -0.06
    .std
    -0.06
     Ubisoft
    -0.06
     Taipei
    -0.06
    Effects
    -0.06
     safest
    -0.06
    Week
    -0.06
    Lim
    -0.05
    forgot
    -0.05
    PDF
    -0.05
    POSITIVE LOGITS
    eden
    0.08
    rie
    0.07
     unparalleled
    0.07
    삼
    0.06
    ęd
    0.06
    0.06
     merg
    0.06
    0.06
    .control
    0.06
     анти
    0.06
    Act Density 0.002%

    No Known Activations