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

    Neuronpedia

    INDEX
    Explanations

    treat to a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    2.59
    ко
    1.90
    든
    1.69
    чем
    1.68
    ന്‍
    1.67
    ка
    1.66
    ws
    1.64
    е
    1.63
    ยอม
    1.63
    сть
    1.61
    POSITIVE LOGITS
    त
    2.12
     thyroid
    2.08
    ום
    2.01
    ्य
    1.99
     phosphorylation
    1.94
    a
    1.93
     sakit
    1.89
     banter
    1.88
    ᴿ
    1.87
     svm
    1.85
    Act Density 0.001%

    No Known Activations