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

    Neuronpedia

    INDEX
    Explanations

    -Type

    np_max-act · gemini-2.0-flash

    The neuron detects MIME-like header fields—specifically “Content-Type” and “Content-Transfer-Encoding” metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rendez
    -0.06
     куст
    -0.06
    Hur
    -0.06
    .FieldName
    -0.06
    Ob
    -0.06
    Choose
    -0.06
    Parents
    -0.06
    jk
    -0.06
    OC
    -0.06
    sword
    -0.06
    POSITIVE LOGITS
    ="$(
    0.07
     پیشینه
    0.07
     Collections
    0.07
     erotiske
    0.07
    	MPI
    0.07
    /include
    0.06
    /{}/
    0.06
    ΗΣ
    0.06
    ικοί
    0.06
     ('\
    0.06
    Act Density 0.000%

    No Known Activations