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

    Neuronpedia

    INDEX
    Explanations

    partial class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dans
    0.42
    HERS
    0.39
     जाय
    0.39
     memperkenalkan
    0.39
    fancy
    0.38
    fortune
    0.38
     niezwy
    0.37
     Businessman
    0.37
     veya
    0.37
    ̣
    0.36
    POSITIVE LOGITS
    Cru
    0.38
    ansom
    0.38
     وبالتالي
    0.38
    ต่อ
    0.38
    须
    0.38
    菘
    0.38
    Also
    0.37
     ethos
    0.37
     JV
    0.37
    Closing
    0.36
    Act Density 0.003%

    No Known Activations