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

    Neuronpedia

    INDEX
    Explanations

    geographic locations and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Appendix
    0.49
     BOOKS
    0.47
    0.45
    APPENDIX
    0.44
    APPEND
    0.43
     Bibliography
    0.43
     varie
    0.43
     Figure
    0.42
    ethics
    0.41
    ໃຈ
    0.41
    POSITIVE LOGITS
     Taiwan
    0.45
    Taiwan
    0.41
    ュー
    0.38
    Equipment
    0.38
    gat
    0.38
     shaving
    0.37
     Jiangsu
    0.37
     liqu
    0.37
    Ghana
    0.36
     causada
    0.36
    Act Density 0.002%

    No Known Activations