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

    Neuronpedia

    INDEX
    Explanations

    your budget or interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Replace
    0.53
     rewrite
    0.45
    Analysis
    0.44
     undermines
    0.43
     obfusc
    0.43
     preprocessing
    0.43
    Error
    0.42
     replace
    0.42
    Theorem
    0.42
    Translation
    0.42
    POSITIVE LOGITS
     budget
    0.66
     interesses
    0.64
    予算
    0.64
     preferencias
    0.62
     бюджет
    0.61
     intereses
    0.60
     tercih
    0.59
     buget
    0.59
     Budget
    0.58
     여행
    0.56
    Act Density 0.190%

    No Known Activations