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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of the substring “test” (in various contexts, whether standalone or embedded in larger words).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Around
    -0.07
     smlou
    -0.06
     king
    -0.06
     around
    -0.06
     smlouvy
    -0.06
     схем
    -0.06
    .crop
    -0.06
     hors
    -0.06
     brigade
    -0.06
     chocol
    -0.06
    POSITIVE LOGITS
     Test
    0.15
     test
    0.15
    Test
    0.14
    etest
    0.11
    .test
    0.11
    test
    0.11
    TEST
    0.11
     tests
    0.11
    	test
    0.10
    Testing
    0.10
    Act Density 0.068%

    No Known Activations