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

    Neuronpedia

    INDEX
    Explanations

    amount of caffeine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solicitar
    0.35
     omnichannel
    0.35
     convivial
    0.35
     facilitar
    0.35
     insolvent
    0.34
     definir
    0.33
     jurid
    0.33
     prosedur
    0.33
     facilita
    0.33
     leverages
    0.32
    POSITIVE LOGITS
    粞
    0.36
    ╿
    0.35
    硞
    0.35
    綪
    0.34
    лки
    0.34
    儸
    0.34
    蕖
    0.32
    釹
    0.32
    這是
    0.32
    𝑜
    0.32
    Act Density 0.000%

    No Known Activations