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

    Neuronpedia

    INDEX
    Explanations

    By

    np_max-act · gemini-2.0-flash

    This neuron activates on JSON object property names (the keys before the colons in package‐metadata blocks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Girls
    -0.07
    Services
    -0.07
    Под
    -0.06
    Operator
    -0.06
     analytic
    -0.06
    Servers
    -0.06
    Girls
    -0.06
     MainForm
    -0.06
    -pencil
    -0.06
     Ders
    -0.06
    POSITIVE LOGITS
     vyt
    0.07
    ?",
    0.06
    )."
    0.06
     intox
    0.06
    δυ
    0.06
    enerator
    0.06
     tape
    0.06
     wav
    0.06
     indefinite
    0.06
    ถนน
    0.06
    Act Density 0.001%

    No Known Activations