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

    Neuronpedia

    INDEX
    Explanations

    APSHOT

    np_max-act · gemini-2.0-flash

    The neuron detects version‐number tokens (numeric version components and qualifiers like “SNAPSHOT”) in XML (POM) files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     burial
    -0.06
     Bryan
    -0.06
    Algorithm
    -0.06
     skirts
    -0.06
     functional
    -0.06
     EC
    -0.06
     Canton
    -0.06
     Consult
    -0.06
     nấu
    -0.06
    (result
    -0.06
    POSITIVE LOGITS
    öt
    0.06
     хв
    0.06
    _insn
    0.06
     다운로드
    0.06
    마사지
    0.06
    oss
    0.06
    ฤษ
    0.06
    станов
    0.06
     야
    0.06
    _push
    0.06
    Act Density 0.001%

    No Known Activations