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

    Neuronpedia

    INDEX
    Explanations

    Configuration

    np_max-act · gemini-2.0-flash

    The neuron fires on MSBuild-style condition expressions, in particular occurrences of the $(Configuration) variable (and related configuration tokens) in project‐file XML.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     가까
    -0.07
     сх
    -0.07
     Thesis
    -0.06
    」「
    -0.06
     leopard
    -0.06
     Leopard
    -0.06
     正
    -0.06
    los
    -0.06
    ávání
    -0.06
     varios
    -0.06
    POSITIVE LOGITS
    ैं.
    0.07
     aust
    0.07
    endencies
    0.07
    ocomplete
    0.06
     punctuation
    0.06
     charismatic
    0.06
    170
    0.06
    unctuation
    0.06
    Appe
    0.06
     assurances
    0.06
    Act Density 0.000%

    No Known Activations