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

    Neuronpedia

    INDEX
    Explanations

    database connection strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    도
    0.59
    0.57
     जलवायु
    0.54
    pppp
    0.53
    宜
    0.52
    ı
    0.52
    ลง
    0.51
     superson
    0.50
     prots
    0.50
    ärts
    0.49
    POSITIVE LOGITS
     Tired
    0.54
    ﺭ
    0.52
    AN
    0.51
     Learned
    0.51
    われた
    0.51
    R
    0.50
    ান
    0.50
     Pandemic
    0.49
    ﺩ
    0.49
    দি
    0.48
    Act Density 0.001%

    No Known Activations