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

    Neuronpedia

    INDEX
    Explanations

    direct deposit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Villa
    0.47
    Landing
    0.46
    Operational
    0.43
    Flight
    0.43
    Tourist
    0.42
    ibernate
    0.42
    WEST
    0.42
     boulevard
    0.42
    Splash
    0.41
    Cay
    0.41
    POSITIVE LOGITS
     next
    0.46
    それぞれの
    0.43
     entries
    0.41
     each
    0.40
     made
    0.39
     thinkers
    0.39
    }
    0.38
     entry
    0.38
     whenever
    0.38
     up
    0.38
    Act Density 0.001%

    No Known Activations