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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects hedging phrases built around “sort of” (i.e. the pattern “sort of […]”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lemma
    -0.07
     ecological
    -0.06
     AppBundle
    -0.06
    (Web
    -0.06
    .runtime
    -0.06
     územ
    -0.06
    sub
    -0.06
    .inputs
    -0.06
    그러
    -0.06
    .forChild
    -0.06
    POSITIVE LOGITS
    ropped
    0.07
     gal
    0.07
    olo
    0.06
    .roll
    0.06
    ()↵
    0.06
     Populate
    0.06
     Phil
    0.06
    (GameObject
    0.06
    640
    0.06
     Te
    0.06
    Act Density 0.012%

    No Known Activations