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

    Neuronpedia

    INDEX
    Explanations

    diagrams and figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bureauc
    -0.06
     Interaction
    -0.06
    نب
    -0.06
    agency
    -0.06
     synchronization
    -0.06
    insky
    -0.06
     toilets
    -0.06
     jurisdiction
    -0.06
     hunted
    -0.06
    isku
    -0.06
    POSITIVE LOGITS
     пес
    0.06
     Sit
    0.06
     філь
    0.06
     regist
    0.06
     ignore
    0.06
     Bias
    0.06
    _reordered
    0.06
     sağlay
    0.06
    /Delete
    0.06
     problemas
    0.06
    Act Density 0.007%

    No Known Activations