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

    Neuronpedia

    INDEX
    Explanations

    habits and routines

    np_max-act · gemini-2.0-flash

    References to habit formation — repeated/routine behaviors becoming automatic or consistent.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31

    The neuron detects language describing the formation or execution of habits and routine behaviors.

    oai_token-act-pair · o4-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    Sr
    -0.07
    面積
    -0.07
     น
    -0.07
     мира
    -0.06
     Isn
    -0.06
     Particularly
    -0.06
     gre
    -0.06
     caucus
    -0.06
     asserts
    -0.06
    \e
    -0.06
    POSITIVE LOGITS
    thalm
    0.07
    .deb
    0.06
    _FE
    0.06
    []"
    0.06
     UIL
    0.06
    “(
    0.06
    �
    0.06
    τή
    0.06
     Permissions
    0.06
    opol
    0.06
    Act Density 0.085%

    No Known Activations