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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attire
    -0.07
     chân
    -0.07
    Лю
    -0.06
     guy
    -0.06
    -bel
    -0.06
    bsites
    -0.06
     pierced
    -0.06
     crunchy
    -0.06
    Hu
    -0.06
    _CE
    -0.06
    POSITIVE LOGITS
    (movie
    0.06
     ciphertext
    0.06
    olecules
    0.06
    pathname
    0.06
     popover
    0.06
    	Response
    0.06
    lock
    0.06
     начала
    0.06
    `↵
    0.06
     Slater
    0.06
    Act Density 0.000%

    No Known Activations