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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases with specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flavorful
    0.60
     goofy
    0.56
     fervor
    0.53
     cognizant
    0.53
     kiddos
    0.53
     tremendous
    0.52
     epicenter
    0.52
     hypothesized
    0.49
     armor
    0.49
     paraly
    0.48
    POSITIVE LOGITS
     HMRC
    1.06
     postcode
    1.00
     adverts
    0.93
    Whilst
    0.92
     motorway
    0.91
     £
    0.89
     unauthorised
    0.89
     timescales
    0.89
     NHS
    0.88
     councillors
    0.86
    Act Density 0.021%

    No Known Activations