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

    Neuronpedia

    INDEX
    Explanations

    percentages, days, or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🐋
    0.78
    ik
    0.77
    $('
    0.77
    rifice
    0.77
    aculate
    0.76
     dragState
    0.75
     conse
    0.75
    ப்படம்
    0.75
    startswith
    0.75
    iaan
    0.74
    POSITIVE LOGITS
     Про
    0.88
     femora
    0.86
    до
    0.80
     О
    0.77
    за
    0.77
    พันธุ์
    0.77
    лары
    0.75
    ್ರಾ
    0.75
     Ο
    0.75
     Προ
    0.75
    Act Density 0.001%

    No Known Activations