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

    Neuronpedia

    INDEX
    Explanations

    aggregation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     circle
    -0.07
    .generator
    -0.06
    더니
    -0.06
     stos
    -0.06
    soup
    -0.06
    :',
    -0.06
    (company
    -0.06
     inbox
    -0.06
    =self
    -0.06
     msm
    -0.06
    POSITIVE LOGITS
    باز
    0.07
    aptop
    0.06
    .week
    0.06
    >]
    0.06
    لع
    0.06
    -Pack
    0.06
     الأخ
    0.06
    Leaders
    0.06
     flexGrow
    0.06
     ROW
    0.06
    Act Density 0.020%

    No Known Activations