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

    Neuronpedia

    INDEX
    Explanations

    enabler or source

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fundamentals
    0.48
     konkrét
    0.48
     Basics
    0.47
     TECHNIQUES
    0.45
     やつ
    0.43
     kalimat
    0.42
     spezif
    0.41
     Techniques
    0.41
    Fundamentals
    0.41
     técnicas
    0.41
    POSITIVE LOGITS
     conduit
    1.08
     source
    1.06
     catalyst
    1.05
     repository
    0.95
    source
    0.91
     provider
    0.89
     facilitator
    0.89
     hub
    0.88
     initiator
    0.88
     catalysts
    0.87
    Act Density 0.688%

    No Known Activations