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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    facts concerning policing and crime incidents.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on the “Document:” header label (and similar meta‐text markers), i.e. it detects section headings or field labels rather than content words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     OCC
    -0.07
    DDD
    -0.06
    bdd
    -0.06
     clipboard
    -0.06
    lines
    -0.06
    .layers
    -0.06
     Arch
    -0.06
    посеред
    -0.06
     pods
    -0.06
    hythm
    -0.06
    POSITIVE LOGITS
    (i
    0.08
    _flash
    0.07
     magically
    0.07
    .');
    0.06
    JKLM
    0.06
    %=
    0.06
     доз
    0.06
    (/[
    0.06
     разв
    0.06
     \''
    0.06
    Act Density 0.004%

    No Known Activations