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

    Neuronpedia

    INDEX
    Explanations

    number four

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Middleware
    -0.09
    Triggered
    -0.09
     Furnace
    -0.08
    FTP
    -0.08
    Handshake
    -0.08
    滚
    -0.08
    -Core
    -0.08
    빛
    -0.08
     Projekte
    -0.08
     saz
    -0.08
    POSITIVE LOGITS
    _dropdown
    0.12
     विकल्प
    0.11
    _options
    0.11
    _answer
    0.10
    _answers
    0.10
     distract
    0.10
     उत्तर
    0.10
     guessing
    0.10
     respostas
    0.10
     मतदान
    0.10
    Act Density 0.016%

    No Known Activations