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

    Neuronpedia

    INDEX
    Explanations

    government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protect
    -0.07
     Bubble
    -0.06
    .projects
    -0.06
    _PHY
    -0.06
     sand
    -0.06
    емые
    -0.06
    (...
    -0.06
    Fly
    -0.06
    endo
    -0.06
     fruits
    -0.06
    POSITIVE LOGITS
    urrent
    0.07
     unload
    0.07
    ivar
    0.06
    shine
    0.06
    *)↵↵
    0.06
     quarterbacks
    0.06
    	sh
    0.06
     government
    0.06
     Vox
    0.06
     messaging
    0.06
    Act Density 0.021%

    No Known Activations