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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “those having.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Epstein
    -0.07
    	found
    -0.06
     truncate
    -0.06
     scratched
    -0.06
     rnd
    -0.06
    	iNdEx
    -0.06
    Nm
    -0.06
    FieldName
    -0.06
    amaged
    -0.06
    Fashion
    -0.06
    POSITIVE LOGITS
     those
    0.07
    обра�
    0.07
    ulação
    0.06
    those
    0.06
    醴
    0.06
    寶
    0.06
    (numbers
    0.06
    StyleSheet
    0.06
     goods
    0.06
     joke
    0.06
    Act Density 0.018%

    No Known Activations