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

    Neuronpedia

    INDEX
    Explanations

    dialing in the UK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Homer
    0.40
     کمان
    0.40
    莹
    0.39
     Confeder
    0.38
    Conf
    0.37
    cJ
    0.36
     interpolated
    0.36
    蔭
    0.36
     Conf
    0.36
    得
    0.35
    POSITIVE LOGITS
     UK
    0.52
     діа
    0.43
     £
    0.43
     Absent
    0.42
     dial
    0.41
     %#
    0.41
     Dial
    0.41
     Jor
    0.40
     Sainsbury
    0.39
    UK
    0.38
    Act Density 0.012%

    No Known Activations