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

    Neuronpedia

    INDEX
    Explanations

    if applicable or necessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     хотя
    0.41
     albeit
    0.40
     meningkatkan
    0.39
     memberikan
    0.38
     cependant
    0.37
     сначала
    0.36
     sedikit
    0.36
     Tuy
    0.36
     educating
    0.36
     chewing
    0.36
    POSITIVE LOGITS
     applicable
    0.57
    applicable
    0.57
     Applicable
    0.47
    如果是
    0.43
     cazul
    0.40
    NewGuid
    0.39
     necessario
    0.38
     necessário
    0.38
     vorhanden
    0.38
    ﷲ
    0.38
    Act Density 0.098%

    No Known Activations