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

    Neuronpedia

    INDEX
    Explanations

    mockingbird and mommy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অস্ট্র
    0.44
     tbody
    0.40
     SQLite
    0.40
     بیرون
    0.39
     defens
    0.39
    ඌ
    0.39
     চিঠ
    0.38
     చక్కెర
    0.38
    FRINGEMENT
    0.38
     鞋
    0.37
    POSITIVE LOGITS
    inp
    0.53
    bird
    0.48
    Mock
    0.42
     mocking
    0.41
    mock
    0.40
    heiser
    0.39
    ெய்
    0.39
    ത്ത്
    0.38
    દ્ધ
    0.38
    死
    0.38
    Act Density 0.005%

    No Known Activations