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

    Neuronpedia

    INDEX
    Explanations

    tree

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gate
    -0.06
    '])
↵
    -0.06
    成绩
    -0.06
    Ent
    -0.06
    '))
↵
    -0.06
    For
    -0.06
    '};↵
    -0.06
    portunity
    -0.06
     leaked
    -0.06
     answered
    -0.06
    POSITIVE LOGITS
    (Stream
    0.07
     adolescence
    0.07
    /free
    0.07
    ーバ
    0.07
     بك
    0.07
    _LINE
    0.07
     markdown
    0.07
     Фран
    0.06
    artisan
    0.06
     tangent
    0.06
    Act Density 0.006%

    No Known Activations