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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    This neuron detects the relative‐clause phrase “who was” as it introduces an age qualifier (e.g. “who was 65 years of age or older”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sci
    -0.06
    -establish
    -0.06
     EPS
    -0.06
     prefect
    -0.06
    ्रच
    -0.06
     melts
    -0.06
     BR
    -0.06
    =["
    -0.05
    apiro
    -0.05
     OST
    -0.05
    POSITIVE LOGITS
     �
    0.07
    sizei
    0.07
    @FXML
    0.06
    αλλ
    0.06
    .properties
    0.06
    τές
    0.06
     Roland
    0.06
     beans
    0.06
    ník
    0.06
    .$
    0.06
    Act Density 0.000%

    No Known Activations