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

    Neuronpedia

    INDEX
    Explanations

    verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     öğ
    -0.07
    醚
    -0.06
    ♔
    -0.06
     cứ
    -0.06
    搖
    -0.06
    orie
    -0.06
     dönem
    -0.06
    ную
    -0.06
     Beatles
    -0.06
    sure
    -0.06
    POSITIVE LOGITS
     вод
    0.08
    _TM
    0.07
    .Comp
    0.07
    $this
    0.07
    二季度
    0.07
    (Roles
    0.07
     timetable
    0.07
     Tencent
    0.07
     Wells
    0.07
     epochs
    0.07
    Act Density 0.023%

    No Known Activations