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

    Neuronpedia

    INDEX
    Explanations

    injections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demonstration
    -0.07
     thunder
    -0.07
     Hunt
    -0.06
     locker
    -0.06
     Como
    -0.06
    $↵
    -0.06
     bob
    -0.06
     el
    -0.06
     reassuring
    -0.06
    .Texture
    -0.06
    POSITIVE LOGITS
    _AspNet
    0.07
    .assertIsNot
    0.07
    )._
    0.06
     beware
    0.06
     �
    0.06
    DialogContent
    0.06
    ————————
    0.06
     인간
    0.06
    _n
    0.06
     사랑
    0.06
    Act Density 0.040%

    No Known Activations