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

    Neuronpedia

    INDEX
    Explanations

    science fiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     инте
    0.50
     Janet
    0.42
    听
    0.41
    进行
    0.40
     Against
    0.39
     Tuesdays
    0.39
     боле
    0.39
     Surreal
    0.38
     ос
    0.38
     Jackets
    0.38
    POSITIVE LOGITS
    })$.
    0.49
    iverso
    0.49
    ives
    0.49
    ut
    0.49
     gunung
    0.48
     mistakes
    0.48
     brotherhood
    0.48
     SAMP
    0.48
    er
    0.46
    ida
    0.46
    Act Density 0.004%

    No Known Activations