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

    Neuronpedia

    INDEX
    Explanations

    history, world, and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Certaines
    0.57
     ஆலய
    0.48
    楦
    0.47
     végétation
    0.47
     பின்பற்ற
    0.47
     آل
    0.47
    ة
    0.46
    atürk
    0.46
     библиоте
    0.45
    }$&$
    0.45
    POSITIVE LOGITS
    gate
    0.46
    way
    0.46
    history
    0.43
    .
    0.43
    world
    0.42
    ay
    0.42
    predicate
    0.41
     history
    0.40
    …
    0.40
     tasked
    0.39
    Act Density 0.004%

    No Known Activations