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

    Neuronpedia

    INDEX
    Explanations

    "you've" / "you've been"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ျ
    0.41
    าร์
    0.40
    र्भ
    0.40
    дона
    0.39
     школу
    0.39
     undermining
    0.39
    azine
    0.38
    imedia
    0.37
     학교
    0.37
    дование
    0.36
    POSITIVE LOGITS
    Baltimore
    0.42
    ッサ
    0.41
    CubeSize
    0.39
    kans
    0.38
    サン
    0.38
    }}{|
    0.38
    JComboBox
    0.38
    Encryption
    0.37
    Marble
    0.37
    Pupp
    0.37
    Act Density 0.001%

    No Known Activations