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

    Neuronpedia

    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辆
    -0.07
    ansible
    -0.07
    iative
    -0.06
    aptic
    -0.06
     brace
    -0.06
     magnificent
    -0.06
    +↵↵
    -0.06
     iteration
    -0.06
     ngàn
    -0.06
    North
    -0.06
    POSITIVE LOGITS
    .Completed
    0.07
     walmart
    0.07
    гля
    0.07
    .abstract
    0.07
    蝘
    0.07
     Carol
    0.07
     Curt
    0.07
    Disposition
    0.07
     QUICK
    0.07
    筷
    0.07
    Act Density 0.045%

    No Known Activations