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

    Neuronpedia

    INDEX
    Explanations

    ""

    np_max-act · gemini-2.0-flash

    The neuron responds to double‐quote characters or quotation marks in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Б
    -0.07
    Eigen
    -0.07
    临
    -0.06
    “I
    -0.06
    iales
    -0.06
    FLICT
    -0.06
    і
    -0.06
    �
    -0.06
    τίου
    -0.06
    lığın
    -0.06
    POSITIVE LOGITS
    ""
    0.07
     Harr
    0.07
     gem
    0.07
     ambiguous
    0.07
     Sullivan
    0.07
    .parentNode
    0.07
     Santa
    0.07
     stares
    0.07
     unrelated
    0.07
    arrow
    0.07
    Act Density 0.007%

    No Known Activations