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

    Neuronpedia

    INDEX
    Explanations

    national action plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ա
    0.52
    üste
    0.51
     aumentando
    0.49
     थिए
    0.48
     zvyš
    0.48
     отдыха
    0.47
     postures
    0.47
     absenteeism
    0.46
     ഭ
    0.46
     क्षति
    0.46
    POSITIVE LOGITS
     accounted
    0.47
     Scotland
    0.43
     qua
    0.41
     Wales
    0.41
    )
    0.41
    чну
    0.40
    분
    0.38
     Endless
    0.38
     Welsh
    0.38
    expansive
    0.38
    Act Density 0.000%

    No Known Activations