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

    Neuronpedia

    INDEX
    Explanations

    banking regulation, human tone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Compat
    0.45
     ở
    0.44
    ات
    0.43
    InRange
    0.43
    Embedded
    0.43
    Placeholder
    0.42
    Mannschaft
    0.42
    ComboBox
    0.42
    োঁ
    0.41
     معمولی
    0.41
    POSITIVE LOGITS
     milj
    0.51
     hence
    0.49
     Explain
    0.48
     ১ম
    0.48
     ह्र
    0.48
     explains
    0.48
     hypothesized
    0.48
     myriad
    0.47
     spiega
    0.47
     hypothes
    0.46
    Act Density 0.006%

    No Known Activations