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

    Neuronpedia

    INDEX
    Explanations

    without explicit qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consenso
    0.46
    駑
    0.44
    合成
    0.43
     deberá
    0.42
     dovrà
    0.40
     consentimiento
    0.38
     deberán
    0.38
     deverá
    0.38
    獲得
    0.37
     tenho
    0.36
    POSITIVE LOGITS
    (('
    0.40
    indices
    0.40
     سكان
    0.40
     column
    0.38
     Nas
    0.38
     too
    0.38
     Six
    0.38
     indices
    0.37
     KPIs
    0.36
     Prince
    0.36
    Act Density 0.000%

    No Known Activations