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

    Neuronpedia

    INDEX
    Explanations

    She was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    פ
    0.46
     회사
    0.44
     тща
    0.44
     flatter
    0.43
    Lem
    0.42
    liert
    0.41
    ঙ্গার
    0.40
     힘들
    0.40
    Rama
    0.39
    UNITY
    0.39
    POSITIVE LOGITS
    रुण
    0.57
    KeyboardMarkup
    0.53
     notes
    0.49
     également
    0.48
    感染
    0.48
    esehatan
    0.48
     entsprechenden
    0.48
     games
    0.47
    新型コロナ
    0.46
     कोविड
    0.45
    Act Density 0.003%

    No Known Activations