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

    Neuronpedia

    INDEX
    Explanations

    organization and readability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Business
    0.46
     Solutions
    0.45
     Innovative
    0.42
     NEEDS
    0.41
     kuni
    0.39
     Brid
    0.39
     Almost
    0.39
     Ways
    0.39
     Entertainment
    0.38
     Compet
    0.38
    POSITIVE LOGITS
     easier
    0.88
     clearer
    0.79
     memudahkan
    0.78
    更容易
    0.77
    方便
    0.74
    便于
    0.73
     avoid
    0.71
    Avoid
    0.70
     claridad
    0.70
     clearest
    0.69
    Act Density 0.054%

    No Known Activations