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

    Neuronpedia

    INDEX
    Explanations

    considering something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Perform
    -0.07
    Americ
    -0.07
     undesirable
    -0.07
    ±
    -0.07
    Dallas
    -0.06
     misuse
    -0.06
     Hall
    -0.06
    -in
    -0.06
     Robotics
    -0.06
     vets
    -0.06
    POSITIVE LOGITS
    -application
    0.07
    ยง
    0.06
    ẫ
    0.06
    iece
    0.06
    ognitive
    0.06
    _SI
    0.06
     стану
    0.06
    _wp
    0.06
    uppy
    0.06
     Newspaper
    0.06
    Act Density 0.030%

    No Known Activations