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

    Neuronpedia

    INDEX
    Explanations

    apply and interpret data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    0.46
     watery
    0.45
    atthena
    0.45
     curvy
    0.45
     soapy
    0.45
    ains
    0.44
    interpr
    0.44
     टूर्
    0.43
     बाहरी
    0.43
     regione
    0.43
    POSITIVE LOGITS
     bukanlah
    0.40
    ហារ
    0.40
     सुद्धा
    0.39
    ické
    0.39
    請問
    0.38
    جة
    0.38
     Gleason
    0.37
     বুকে
    0.37
    还是要
    0.37
    年モデル
    0.36
    Act Density 0.000%

    No Known Activations