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

    Neuronpedia

    INDEX
    Explanations

    people and relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sk
    -0.06
     jedna
    -0.06
    Proj
    -0.06
     státní
    -0.06
    undi
    -0.06
     denně
    -0.06
    lemetry
    -0.06
     Apparel
    -0.06
     багатьох
    -0.06
    지막
    -0.06
    POSITIVE LOGITS
    (bottom
    0.07
     agree
    0.07
     tried
    0.07
     submits
    0.07
    	mv
    0.06
     replace
    0.06
    '}↵
    0.06
    (H
    0.06
     [...
    0.06
    quarters
    0.06
    Act Density 0.016%

    No Known Activations