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

    Neuronpedia

    INDEX
    Explanations

    wikipedia references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IO
    0.84
     cacao
    0.82
     tuner
    0.79
     customer
    0.79
     chocolates
    0.78
     FCM
    0.78
     treasures
    0.77
     Authentication
    0.77
     authentication
    0.77
     javac
    0.76
    POSITIVE LOGITS
    Wikipedia
    2.82
     Wikipedia
    2.64
     wikipedia
    2.40
    wikipedia
    2.34
     wiki
    2.19
     Wikiped
    2.19
    wiki
    2.18
     Wiki
    2.17
     Вики
    2.10
    Wiki
    2.06
    Act Density 0.055%

    No Known Activations