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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    USA
    -0.06
     juris
    -0.06
     accomplishments
    -0.06
     optimal
    -0.06
    cole
    -0.06
    193
    -0.06
    		↵		↵		↵
    -0.06
    umbed
    -0.06
     ego
    -0.06
    043
    -0.06
    POSITIVE LOGITS
    러스
    0.06
    .Node
    0.06
     Wes
    0.06
     Цент
    0.06
    .surname
    0.06
    WND
    0.06
    _directory
    0.06
     Predict
    0.06
    reo
    0.06
    ену
    0.06
    Act Density 0.492%

    No Known Activations