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

    Neuronpedia

    INDEX
    Explanations

    aging

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the Maven POM “packaging” tag (i.e. the word “packaging” split into “pack” and “aging”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ineTransform
    -0.07
    079
    -0.07
     ücret
    -0.07
    てい
    -0.07
     Doğum
    -0.07
    icol
    -0.07
    주소
    -0.06
     تط
    -0.06
    suming
    -0.06
    ені
    -0.06
    POSITIVE LOGITS
     swirling
    0.06
     STORAGE
    0.06
    input
    0.06
    COVER
    0.06
    _mark
    0.06
    particles
    0.06
    527
    0.06
     Greek
    0.05
    ﾆ
    0.05
    Black
    0.05
    Act Density 0.000%

    No Known Activations