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

    Neuronpedia

    INDEX
    Explanations

    sql insert values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    埂
    0.40
    Clan
    0.40
    Cards
    0.40
     सम्प
    0.40
     Elat
    0.40
    Tank
    0.39
    рыва
    0.39
    悝
    0.39
     вокруг
    0.39
    Meng
    0.39
    POSITIVE LOGITS
     values
    0.66
     valores
    0.57
    values
    0.56
     inserted
    0.54
    挿
    0.54
     Values
    0.53
     VALUES
    0.52
     Inserting
    0.50
     value
    0.49
     insertion
    0.48
    Act Density 0.028%

    No Known Activations