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

    Neuronpedia

    INDEX
    Explanations

    singing and singer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ก
    1.35
     was
    1.09
    ק
    0.96
    ن
    0.95
    ും
    0.90
    م
    0.89
    น
    0.89
    ール
    0.88
     eine
    0.86
     erhöhen
    0.86
    POSITIVE LOGITS
     singers
    1.16
     singing
    1.08
     vocalist
    1.03
     singer
    1.01
     I
    1.00
     Singing
    1.00
    di
    0.97
    ja
    0.96
     cantante
    0.89
    dat
    0.85
    Act Density 0.017%

    No Known Activations