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

    Neuronpedia

    INDEX
    Explanations

    short breaks between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yakın
    0.43
     dekat
    0.42
     Close
    0.40
    onej
    0.40
     close
    0.40
    ารณา
    0.38
    Close
    0.38
     근
    0.38
     thẩm
    0.37
    齐
    0.37
    POSITIVE LOGITS
     between
    2.23
     между
    2.17
     Between
    2.13
    Between
    2.09
    between
    2.06
     між
    2.06
     zwischen
    1.98
     BETWEEN
    1.97
     tussen
    1.95
     mellom
    1.92
    Act Density 0.093%

    No Known Activations