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

    Neuronpedia

    INDEX
    Explanations

    headings for assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ન
    0.46
     STEELS
    0.46
    ක
    0.45
     сотруд
    0.45
    হাম্মদ
    0.45
     сотрудников
    0.45
     Darryl
    0.44
     वैदिक
    0.44
    PhoneNumber
    0.43
    panic
    0.43
    POSITIVE LOGITS
    6
    0.40
    bis
    0.40
    ensioni
    0.39
     lég
    0.39
     schw
    0.38
    دن
    0.38
     নিজেও
    0.38
    ือ
    0.37
     മഴ
    0.37
     θέση
    0.37
    Act Density 0.012%

    No Known Activations