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

    Neuronpedia

    INDEX
    Explanations

    doorway pages, airport, URL, edits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yser
    0.54
     flourished
    0.53
     emerged
    0.52
     steeped
    0.52
    ेक्स
    0.51
    ጠቃ
    0.50
     leaped
    0.48
    食べ
    0.48
    ंदे
    0.48
    持ち
    0.47
    POSITIVE LOGITS
    或者
    0.44
     April
    0.43
    So
    0.42
     Similarly
    0.41
    Fortunately
    0.41
    Closing
    0.41
    避免
    0.40
     Fm
    0.40
    ’).
    0.40
    Page
    0.39
    Act Density 0.001%

    No Known Activations