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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on document-structure labels and section headings (e.g. “INSTRUCTIONS:” and “BACKGROUND:”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .square
    -0.07
     drinks
    -0.07
    holm
    -0.07
    Om
    -0.07
    emergency
    -0.07
     wash
    -0.07
    .sum
    -0.07
    Boolean
    -0.06
    Reducer
    -0.06
     rotates
    -0.06
    POSITIVE LOGITS
     지난
    0.07
    _above
    0.07
     이는
    0.07
     проведения
    0.06
    ','#
    0.06
     Cler
    0.06
    场
    0.06
     großen
    0.06
     Institut
    0.06
     estad
    0.06
    Act Density 0.027%

    No Known Activations