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

    Neuronpedia

    INDEX
    Explanations

    their, belonging, instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MANAGER
    0.41
    Funds
    0.40
     comparisons
    0.39
     rifles
    0.38
     murdering
    0.38
    funds
    0.37
    ायत
    0.37
    compar
    0.37
     Compar
    0.36
     비교
    0.36
    POSITIVE LOGITS
    他們的
    0.47
    他们的
    0.43
    羵
    0.42
     এদের
    0.41
     THEIR
    0.40
     Their
    0.40
     ያላቸው
    0.40
     тому
    0.39
     घरे
    0.39
    चरण
    0.39
    Act Density 0.000%

    No Known Activations