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

    Neuronpedia

    INDEX
    Explanations

    disputed territory and independence movements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unprecedented
    0.47
     unmistakable
    0.43
     Telegram
    0.42
     deleg
    0.42
     ведь
    0.40
     unmistak
    0.40
     refinancing
    0.39
    rivial
    0.38
    ?!
    0.38
    irmat
    0.38
    POSITIVE LOGITS
    {|
    0.41
    Sear
    0.39
    ርሃ
    0.38
    Thumb
    0.38
    泻
    0.38
    prit
    0.37
     Camera
    0.37
    BlockUsed
    0.36
     अर्ध
    0.36
    Although
    0.36
    Act Density 0.002%

    No Known Activations