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

    Neuronpedia

    INDEX
    Explanations

    created by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elands
    0.71
     നമഃ
    0.70
     MSI
    0.67
     PETER
    0.66
    ignés
    0.66
    uniary
    0.65
    ophane
    0.65
    ujukan
    0.65
    اديه
    0.64
    ುವುದು
    0.64
    POSITIVE LOGITS
    D
    0.56
     উড়
    0.50
    monkey
    0.49
    Labor
    0.48
    R
    0.47
    S
    0.46
     উঠলাম
    0.43
     Sorg
    0.43
    Monkey
    0.43
    <0x93>
    0.42
    Act Density 0.131%

    No Known Activations