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

    Neuronpedia

    INDEX
    Explanations

    future verbs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     करतात
    0.77
    վում
    0.75
     जातात
    0.66
     होतात
    0.66
     देतात
    0.66
     suggesting
    0.64
    都是
    0.63
     असतात
    0.63
     Were
    0.62
     येतात
    0.62
    POSITIVE LOGITS
     estará
    1.59
     sẽ
    1.52
     dará
    1.42
     será
    1.38
     will
    1.37
     seguirá
    1.33
     tendrá
    1.32
     akan
    1.28
     terá
    1.26
     będzie
    1.25
    Act Density 0.075%

    No Known Activations