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

    Neuronpedia

    INDEX
    Explanations

    interest rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infarct
    0.86
     bartenders
    0.85
     emig
    0.84
     forklift
    0.82
     altar
    0.82
     plumbers
    0.81
     rest
    0.80
     deputies
    0.80
     referees
    0.80
     defend
    0.79
    POSITIVE LOGITS
    ке
    0.73
    ً
    0.66
    rate
    0.65
    uesto
    0.64
    ים
    0.63
    setContentType
    0.63
    율
    0.63
    व
    0.61
    ние
    0.61
     которое
    0.61
    Act Density 0.001%

    No Known Activations