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

    Neuronpedia

    INDEX
    Explanations

    libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tulsa
    -0.07
     تنها
    -0.07
     temas
    -0.07
     sur
    -0.06
     suprem
    -0.06
     손을
    -0.06
     Stunden
    -0.06
    _creator
    -0.06
     году
    -0.06
     criticizing
    -0.06
    POSITIVE LOGITS
     boxed
    0.07
    .reference
    0.07
     anom
    0.06
    UMMY
    0.06
     channels
    0.06
    oron
    0.06
     complimentary
    0.06
     microscope
    0.06
    _Show
    0.06
    .nil
    0.06
    Act Density 0.085%

    No Known Activations