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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۲۷
    -0.07
     appeared
    -0.07
     المو
    -0.07
     Changing
    -0.07
     upfront
    -0.07
     playground
    -0.07
     Comple
    -0.07
    ấp
    -0.07
     hizo
    -0.06
     Prior
    -0.06
    POSITIVE LOGITS
    ibbon
    0.07
     verir
    0.06
    icut
    0.06
     فوق
    0.06
     留
    0.06
    licit
    0.06
     Üniversitesi
    0.06
    øj
    0.06
    _trajectory
    0.06
     kleine
    0.06
    Act Density 0.016%

    No Known Activations