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

    Neuronpedia

    INDEX
    Explanations

    transferring knowledge and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rugg
    0.53
    ying
    0.52
    ate
    0.48
    य
    0.47
    om
    0.46
    icing
    0.46
     开
    0.46
     Yue
    0.44
     Hä
    0.44
    vä
    0.44
    POSITIVE LOGITS
     переда
    1.26
    传递
    1.17
     전달
    1.16
     transfer
    1.14
     transmit
    1.12
    Transfer
    1.09
     передачи
    1.06
    transfer
    1.05
     transmission
    1.04
    伝
    1.03
    Act Density 0.209%

    No Known Activations