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

    Neuronpedia

    INDEX
    Explanations

    pose

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of yoga pose instructions—especially pose names and related body‐part cues.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Burlington
    -0.07
    udur
    -0.07
    IBLE
    -0.07
     infusion
    -0.07
     перес
    -0.07
    olor
    -0.07
    undra
    -0.07
    installed
    -0.06
    (contract
    -0.06
     dicts
    -0.06
    POSITIVE LOGITS
    BeforeEach
    0.07
    =`
    0.06
     somewhat
    0.06
     *(*
    0.06
    -taking
    0.06
    	        ↵
    0.06
    ::$_
    0.06
    ْل
    0.06
    bigint
    0.06
    (SYS
    0.06
    Act Density 0.008%

    No Known Activations