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

    Neuronpedia

    INDEX
    Explanations

    agatha Christie and Eurovision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    0.91
    ور
    0.86
    р
    0.72
    vecb
    0.69
    chsler
    0.67
    ра
    0.66
    ш
    0.66
    㑓
    0.66
    طان
    0.65
    या
    0.63
    POSITIVE LOGITS
    ↵↵
    0.81
    לי
    0.78
    }_
    0.76
    '
    0.75
    _
    0.74
    and
    0.71
     questa
    0.69
     ל
    0.69
     และ
    0.69
     ק
    0.68
    Act Density 0.001%

    No Known Activations