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

    Neuronpedia

    INDEX
    Explanations

    below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     here
    1.01
     tutaj
    0.99
     tady
    0.92
    以上の
    0.90
    here
    0.89
     above
    0.87
     underground
    0.87
     aqui
    0.87
     ici
    0.86
     backend
    0.85
    POSITIVE LOGITS
    👇
    1.01
     મુજબ
    0.96
    लभ
    0.95
    iende
    0.94
    ᱼ
    0.94
    ജാ
    0.92
     كيف
    0.92
    uigen
    0.91
    䣬
    0.91
    oa
    0.90
    Act Density 0.019%

    No Known Activations