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

    Neuronpedia

    INDEX
    Explanations

    commemorating, founded, reserved for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiddos
    0.87
     impactful
    0.73
     proactively
    0.73
    不仅仅
    0.70
     väldigt
    0.70
     skillset
    0.70
     굉장히
    0.67
     leverages
    0.65
     нужно
    0.64
     davvero
    0.63
    POSITIVE LOGITS
     chiefly
    0.64
     ibid
    0.55
     variously
    0.55
     considerably
    0.52
     commemorate
    0.52
     probably
    0.52
     began
    0.51
     three
    0.51
     principally
    0.51
     നിരവധി
    0.50
    Act Density 0.001%

    No Known Activations