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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swallowing
    -0.07
     Multip
    -0.07
     sant
    -0.06
    Deck
    -0.06
    lat
    -0.06
     smarter
    -0.06
    standing
    -0.06
    -fly
    -0.06
     Stable
    -0.06
    LAT
    -0.06
    POSITIVE LOGITS
     Research
    0.15
     research
    0.15
    Research
    0.14
    research
    0.09
    SEARCH
    0.09
     researcher
    0.09
     pesquisa
    0.08
     work
    0.08
    feedback
    0.08
    search
    0.08
    Act Density 0.048%

    No Known Activations