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

    Neuronpedia

    INDEX
    Explanations

    your or subsequent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.47
     να
    0.46
    种种
    0.45
    ibusdam
    0.44
    5
    0.43
    with
    0.43
    specific
    0.43
    6
    0.43
    head
    0.42
    state
    0.41
    POSITIVE LOGITS
     आपका
    0.50
     futuros
    0.46
     undoubtedly
    0.45
    आपका
    0.45
     vaš
    0.45
     your
    0.44
     впоследствии
    0.44
     overall
    0.43
    无论
    0.43
    Ple
    0.43
    Act Density 0.075%

    No Known Activations