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

    Neuronpedia

    INDEX
    Explanations

    describing components or characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бизнеса
    0.47
    市場
    0.45
    markets
    0.43
     финансо
    0.43
     финанси
    0.43
     покупать
    0.43
     pagare
    0.43
    government
    0.42
     деньги
    0.42
    businessman
    0.41
    POSITIVE LOGITS
     indicate
    0.47
     indicates
    0.45
     indicating
    0.45
    ↵
    0.42
     components
    0.41
     Indicates
    0.41
     discoloration
    0.39
     the
    0.39
     hypothesized
    0.38
     interface
    0.38
    Act Density 0.000%

    No Known Activations