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

    Neuronpedia

    INDEX
    Explanations

    two hot topics, two more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compresses
    0.68
     groaned
    0.68
    Boost
    0.65
     milled
    0.65
    所谓的
    0.64
    भाजपा
    0.63
     cour
    0.63
    8
    0.62
    保存
    0.62
    ৬
    0.61
    POSITIVE LOGITS
     ਤ
    0.89
    ANG
    0.88
     необходимые
    0.86
    PAAm
    0.82
    ным
    0.79
    IVING
    0.78
    ার্ভ
    0.78
     dirigir
    0.78
    ﮏ
    0.77
     necessários
    0.76
    Act Density 0.001%

    No Known Activations