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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the term “base,” as in phrases like “customer base” or “global base.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ’une
    -0.07
     hãng
    -0.07
    'une
    -0.07
     Layout
    -0.06
    Trans
    -0.06
    .Auth
    -0.06
     Witt
    -0.06
     meter
    -0.06
     dividends
    -0.06
    cript
    -0.06
    POSITIVE LOGITS
     중요한
    0.07
    .communication
    0.07
     �
    0.07
    怕
    0.07
     falsehood
    0.07
    ++↵
    0.06
    طقة
    0.06
    aggio
    0.06
    �
    0.06
    「あ
    0.06
    Act Density 0.019%

    No Known Activations