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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    This neuron detects Android XML style/resource `<item name="…">` declarations (the `<item name="…">` tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Lease
    -0.07
     Reese
    -0.06
     Sand
    -0.06
    ≥
    -0.06
     Аф
    -0.06
    ].'
    -0.06
    (df
    -0.06
    (ls
    -0.06
     Ruf
    -0.05
     faded
    -0.05
    POSITIVE LOGITS
    ING
    0.07
    ازي
    0.07
    izedName
    0.07
    日本
    0.06
    di
    0.06
    topic
    0.06
    329
    0.06
    ighborhood
    0.06
     datetime
    0.06
    َم
    0.06
    Act Density 0.001%

    No Known Activations