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

    Neuronpedia

    INDEX
    Explanations

    golden gate bridge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     he
    0.37
     their
    0.36
     해당
    0.36
     monoton
    0.35
     it
    0.34
     brunt
    0.34
     उनके
    0.34
     তখন
    0.34
     전체
    0.34
     millimeters
    0.33
    POSITIVE LOGITS
    Philippines
    0.46
    中国
    0.42
    University
    0.41
     മഹാ
    0.40
    Aff
    0.39
    Institute
    0.38
    عهد
    0.38
    Irish
    0.38
    of
    0.37
    West
    0.37
    Act Density 0.029%

    No Known Activations