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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash

    The neuron detects phrases referring to “best interests,” especially in legal contexts about what serves someone (often a child) best.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     रह
    -0.06
     aktu
    -0.06
    -0.06
     tags
    -0.06
    ですが
    -0.06
    intage
    -0.06
    crollView
    -0.06
    PROCESS
    -0.06
    mouseout
    -0.06
    	stats
    -0.06
    POSITIVE LOGITS
    ॉक
    0.07
     эти
    0.07
     Northern
    0.07
     SqlDataReader
    0.07
    VERTISEMENT
    0.06
     dos
    0.06
    JM
    0.06
    าล
    0.06
    =./
    0.06
     Nos
    0.06
    Act Density 0.007%

    No Known Activations