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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nineteenth
    -0.07
     ['$
    -0.07
    [Boolean
    -0.07
    ("*
    -0.07
    /node
    -0.06
    ('*
    -0.06
    allenges
    -0.06
     Rod
    -0.06
    [res
    -0.06
     '';
↵
    -0.06
    POSITIVE LOGITS
    Marca
    0.07
     широк
    0.07
    ισμού
    0.06
    FullPath
    0.06
    wendung
    0.06
     줄
    0.06
    _IPV
    0.06
    specifier
    0.06
     كامل
    0.06
    Архів
    0.06
    Act Density 0.078%

    No Known Activations