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

    Neuronpedia

    INDEX
    Explanations

    multilingual conjunctions and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cliquant
    0.21
    0.21
     Cumm
    0.18
     aguas
    0.18
     immunized
    0.17
     DQN
    0.17
     utilisent
    0.17
    ㅠ
    0.17
     thaliana
    0.17
    ?
    0.17
    POSITIVE LOGITS
    and
    0.29
     এবং
    0.29
    на
    0.28
    や
    0.28
     and
    0.27
     và
    0.27
     in
    0.26
     or
    0.25
     и
    0.25
     в
    0.25
    Act Density 1.212%

    No Known Activations