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

    Neuronpedia

    INDEX
    Explanations

    :/

    np_max-act · gemini-2.0-flash

    This neuron detects Docker-compose volume mount syntax—host:path mappings in service definitions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -space
    -0.09
     Polo
    -0.07
     tempo
    -0.06
    销售
    -0.06
     peril
    -0.06
     Savage
    -0.06
     vote
    -0.06
    /base
    -0.06
     sce
    -0.06
     MMA
    -0.06
    POSITIVE LOGITS
     AudioSource
    0.07
     [<
    0.07
    (ListNode
    0.07
    -remove
    0.07
    那种
    0.07
     сх
    0.07
    ยาน
    0.06
    .dgv
    0.06
     cancelButtonTitle
    0.06
     FixedUpdate
    0.06
    Act Density 0.001%

    No Known Activations