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

    Neuronpedia

    INDEX
    Explanations

    final answer:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     folks
    0.76
     бизне
    0.71
     tradeoff
    0.70
    Actual
    0.69
     confiar
    0.68
    AccountNumber
    0.68
    SourceIP
    0.68
     Accounts
    0.67
    Counts
    0.67
    Mag
    0.66
    POSITIVE LOGITS
     predisposition
    0.93
    Repartition
    0.87
    imetric
    0.84
     remuneration
    0.84
     duly
    0.81
    intervention
    0.79
     adimensional
    0.79
     употреб
    0.77
    imetry
    0.77
    Subsequently
    0.77
    Act Density 0.041%

    No Known Activations