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

    Neuronpedia

    INDEX
    Explanations

    Korean connectors

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    వి
    0.63
    வை
    0.61
    வையும்
    0.47
    வைய
    0.42
    వ
    0.39
    வைப்
    0.38
    ன
    0.38
    వో
    0.38
    ENES
    0.38
    Ві
    0.36
    POSITIVE LOGITS
     데
    2.03
    데
    1.80
    는데
    1.56
     하는데
    1.45
     있는데
    1.39
    인데
    1.35
    เด
    1.34
     ده
    1.32
    하는데
    1.27
    운데
    1.24
    Act Density 0.000%

    No Known Activations