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

    Neuronpedia

    INDEX
    Explanations

    internal project communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Its
    0.53
     nuove
    0.49
    städter
    0.49
    anilide
    0.46
     പിന്തു
    0.46
    はじ
    0.45
     vogliono
    0.45
    ᱼ
    0.45
    BottomOf
    0.45
     აღმასრულ
    0.45
    POSITIVE LOGITS
     activities
    0.56
     (
    0.53
     रहकर
    0.52
     tests
    0.51
     tribulations
    0.49
    5
    0.49
     auctions
    0.49
     interne
    0.48
     happenings
    0.48
     micro
    0.48
    Act Density 0.103%

    No Known Activations