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

    Neuronpedia

    INDEX
    Explanations

    slice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nella
    -0.07
    .ne
    -0.07
    	pre
    -0.07
    ]")↵
    -0.07
    .ro
    -0.07
    .Percent
    -0.07
    River
    -0.06
     shopper
    -0.06
     Beginners
    -0.06
    Leaders
    -0.06
    POSITIVE LOGITS
     Millet
    0.06
    τικό
    0.06
    fone
    0.06
    폰
    0.06
    Sink
    0.06
    �
    0.06
    gressor
    0.06
     народ
    0.06
    _clients
    0.06
    folk
    0.06
    Act Density 0.000%

    No Known Activations