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

    Neuronpedia

    INDEX
    Explanations

    Ctrl + Shift + Esc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Interface
    0.41
     interfaces
    0.39
    idone
    0.38
     substantive
    0.37
     ileti
    0.37
     interfacing
    0.36
    STRUCTOR
    0.36
    Interfaces
    0.36
    ('.',
    0.36
     facilitators
    0.36
    POSITIVE LOGITS
     Trabalho
    0.45
    ේ
    0.42
     warranty
    0.42
    Warranty
    0.42
     Copyright
    0.41
     product
    0.41
     Trabal
    0.40
    Product
    0.40
     Produkt
    0.39
     Product
    0.39
    Act Density 0.001%

    No Known Activations