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

    Neuronpedia

    INDEX
    Explanations

    flexible use of assets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    綃
    0.45
     Laboratory
    0.42
     Learned
    0.41
     Audience
    0.41
    实验室
    0.40
     learned
    0.39
    Semi
    0.39
     mł
    0.38
     Neuroscience
    0.38
    über
    0.38
    POSITIVE LOGITS
    fixtures
    0.38
    soever
    0.37
    イト
    0.37
     fixtures
    0.36
    리면
    0.36
     ВС
    0.35
    ζ
    0.35
    ONES
    0.35
    nucle
    0.34
    venidas
    0.34
    Act Density 0.003%

    No Known Activations