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

    Neuronpedia

    INDEX
    Explanations

    continue following text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    くちゃ
    1.73
    OM
    1.63
    ebilir
    1.63
    RAchievement
    1.57
    🧿
    1.57
    गोरि
    1.54
    م
    1.53
    RIM
    1.51
     Использу
    1.51
    ÈRE
    1.50
    POSITIVE LOGITS
    k
    2.00
    pt
    1.92
    it
    1.69
    f
    1.65
    ють
    1.63
    ี
    1.63
     Simultaneously
    1.63
     Although
    1.61
     Our
    1.59
    ী
    1.59
    Act Density 0.029%

    No Known Activations