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

    Neuronpedia

    INDEX
    Explanations

    right-click on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     владе
    0.43
     ইত্যাদি
    0.42
     consideramos
    0.37
     нередко
    0.37
     развития
    0.37
    などに
    0.36
    浱
    0.36
    +"/"+
    0.36
    நாம்
    0.36
     входят
    0.36
    POSITIVE LOGITS
     cloud
    0.40
    ικη
    0.38
    器
    0.37
    cloud
    0.36
    াপুর
    0.36
     MP
    0.36
     receiver
    0.35
     whatsoever
    0.35
     onboarding
    0.35
    mp
    0.34
    Act Density 0.002%

    No Known Activations