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

    Neuronpedia

    INDEX
    Explanations

    occurred after events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icrous
    0.49
     kvůli
    0.49
     L
    0.47
    にします
    0.45
     {//
    0.44
    {//
    0.44
     zaradi
    0.43
     preços
    0.43
     preço
    0.42
     cinemas
    0.42
    POSITIVE LOGITS
     occurred
    0.43
    셨
    0.43
     कब
    0.42
     امد
    0.42
     egyéb
    0.41
     事件
    0.41
    וס
    0.41
    事件
    0.40
    是非
    0.40
     程序
    0.40
    Act Density 0.005%

    No Known Activations