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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron fires on words naming communal infrastructure or services (e.g., sanitation, education, healthcare, parks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -light
    -0.06
     client
    -0.06
     Des
    -0.06
    -security
    -0.06
    watch
    -0.06
    'Neill
    -0.06
    557
    -0.06
     Limits
    -0.06
     Watch
    -0.06
    Watch
    -0.06
    POSITIVE LOGITS
    .AbsoluteConstraints
    0.07
     krb
    0.07
    :CGRectMake
    0.06
    aneously
    0.06
     pomp
    0.06
    必要
    0.06
     ogs
    0.06
    <Animator
    0.06
     окра
    0.06
    SKIP
    0.06
    Act Density 0.136%

    No Known Activations