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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     روند
    -0.07
    сього
    -0.07
    LR
    -0.07
     Pax
    -0.07
     kalan
    -0.07
     село
    -0.07
     inflammation
    -0.07
     eb
    -0.07
     Quad
    -0.07
     dangers
    -0.07
    POSITIVE LOGITS
     داخلی
    0.06
     outreach
    0.06
    {!!
    0.06
    227
    0.06
    \S
    0.05
    arrays
    0.05
     Settings
    0.05
    �
    0.05
    工具
    0.05
     inspections
    0.05
    Act Density 0.000%

    No Known Activations