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

    Neuronpedia

    INDEX
    Explanations

    electrical circuits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retrospect
    -0.09
    Southern
    -0.08
    reeze
    -0.08
     Southern
    -0.08
     grooming
    -0.08
     retrospective
    -0.08
    ships
    -0.08
    .buf
    -0.08
     Survival
    -0.08
     flattering
    -0.08
    POSITIVE LOGITS
     विद्य
    0.10
     electrically
    0.09
     plas
    0.09
     listrik
    0.08
    प्रत
    0.08
     punched
    0.08
    이버
    0.08
     Kelvin
    0.08
    電
    0.08
     ವಿದ್ಯ
    0.08
    Act Density 0.040%

    No Known Activations