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

    Neuronpedia

    INDEX
    Explanations

    future action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     быть
    0.98
     been
    0.90
     fain
    0.83
     ideally
    0.81
     helping
    0.81
    стить
    0.80
    നി
    0.79
     βοη
    0.79
    接过
    0.78
     टि
    0.77
    POSITIVE LOGITS
     jsem
    0.83
    tram
    0.83
     ću
    0.83
    тро
    0.81
    communities
    0.79
     mamy
    0.79
     वहीं
    0.79
     seguimos
    0.78
     checkpoints
    0.77
    problems
    0.77
    Act Density 0.083%

    No Known Activations