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

    Neuronpedia

    INDEX
    Explanations

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sim
    -0.07
    �
    -0.07
     dó
    -0.07
    >&
    -0.06
    :↵↵↵↵
    -0.06
    _BUCKET
    -0.06
    	timeout
    -0.06
    Sea
    -0.06
     одного
    -0.06
    ène
    -0.06
    POSITIVE LOGITS
    jf
    0.07
    -Za
    0.06
     İstanbul
    0.06
    /GL
    0.06
     [#
    0.06
    と思
    0.06
     Sadece
    0.06
    ğın
    0.06
    Выб
    0.06
    您
    0.05
    Act Density 0.012%

    No Known Activations