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

    Neuronpedia

    INDEX
    Explanations

    users and prevent harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gesamt
    0.47
     সবকিছু
    0.45
    深化
    0.45
    嬗
    0.45
     María
    0.43
     anlaş
    0.43
     verità
    0.42
     keseluruhan
    0.42
    fetchAll
    0.41
    وازن
    0.41
    POSITIVE LOGITS
    ot
    0.55
     iyong
    0.49
    emore
    0.48
    ock
    0.47
     subscript
    0.46
    u
    0.46
    if
    0.46
    vert
    0.45
    card
    0.45
     indicating
    0.44
    Act Density 0.016%

    No Known Activations