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

    Neuronpedia

    INDEX
    Explanations

    programming terms and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Elektrokh
    0.35
     thoracique
    0.34
    طه
    0.32
     thérapeut
    0.31
     zvyš
    0.30
    脓
    0.29
     cotid
    0.29
    🥅
    0.29
    猞
    0.29
     नाइट्रोजन
    0.29
    POSITIVE LOGITS
    Data
    0.39
     new
    0.36
    Factory
    0.36
     model
    0.34
    Form
    0.33
    class
    0.32
    Config
    0.32
    Client
    0.31
    Model
    0.31
    Manager
    0.31
    Act Density 0.108%

    No Known Activations