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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash

    This neuron activates on parts of HTTP(S)‐style web addresses (URI/IRI tokens such as “http,” “www,” “.org,” numeric year components, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ної
    -0.07
    purpose
    -0.06
     genel
    -0.06
     státu
    -0.06
    forge
    -0.06
    agas
    -0.06
    mounted
    -0.05
    _den
    -0.05
     wiped
    -0.05
    .fac
    -0.05
    POSITIVE LOGITS
    _AUT
    0.07
    Κ
    0.06
    (!
    0.06
    _CB
    0.06
    @"↵
    0.06
     lad
    0.06
     ingl
    0.06
    _logic
    0.06
     加
    0.06
     useNewUrlParser
    0.06
    Act Density 0.003%

    No Known Activations