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

    Neuronpedia

    INDEX
    Explanations

    UK national topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পৃথিবীর
    0.41
    ത്തിന്റെ
    0.40
    也在
    0.40
     nontrivial
    0.39
    タ
    0.39
    inį
    0.39
    ̀ng
    0.38
    醬
    0.38
    できない
    0.38
    hence
    0.38
    POSITIVE LOGITS
     postcode
    0.77
     UK
    0.70
     £
    0.66
     nought
    0.64
     adverts
    0.61
     programme
    0.59
     undoubt
    0.59
     NHS
    0.57
     motorway
    0.57
     Vaux
    0.56
    Act Density 0.004%

    No Known Activations