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

    Neuronpedia

    INDEX
    Explanations

    describing origins or construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Quaternion
    0.41
     آد
    0.40
     analges
    0.39
    勾
    0.38
    ه
    0.38
    abat
    0.38
    potato
    0.36
     وحتى
    0.36
    pok
    0.36
    ?\\
    0.36
    POSITIVE LOGITS
     remembered
    0.44
     Pool
    0.41
     Европей
    0.41
    ке
    0.39
    órc
    0.39
     lembrar
    0.38
    Рабо
    0.38
     தேசிய
    0.38
    rocław
    0.38
     रो
    0.38
    Act Density 0.001%

    No Known Activations