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

    Neuronpedia

    INDEX
    Explanations

    locations of offices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.64
    eding
    0.60
    アー
    0.53
    K
    0.52
     auto
    0.51
    क
    0.51
     a
    0.49
    الت
    0.49
    است
    0.49
    k
    0.49
    POSITIVE LOGITS
     Offices
    0.82
     OFFICES
    0.73
     Trichodesmium
    0.69
    т
    0.67
     offices
    0.66
     WordPerfect
    0.65
    ション
    0.64
     mensuales
    0.64
     Werbung
    0.63
    ThoughtData
    0.63
    Act Density 0.001%

    No Known Activations