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

    Neuronpedia

    INDEX
    Explanations

    say "static"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    208
    -0.08
     Пер
    -0.07
    Address
    -0.07
     Hughes
    -0.07
    222
    -0.07
    ATAB
    -0.07
    _settings
    -0.07
    атег
    -0.06
     movable
    -0.06
    ("-
    -0.06
    POSITIVE LOGITS
     chậm
    0.06
    िछ
    0.06
     پروژه
    0.06
     maç
    0.06
     Go
    0.06
     gazet
    0.06
     Nor
    0.06
    Conversation
    0.05
     bloom
    0.05
     oyn
    0.05
    Act Density 0.018%

    No Known Activations