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

    Neuronpedia

    INDEX
    Explanations

    machine learning / optimization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Camera
    -0.08
    Receive
    -0.08
    receive
    -0.08
    Celebr
    -0.08
    Recv
    -0.08
    _de
    -0.08
    Received
    -0.07
    -.
    -0.07
    declare
    -0.07
    ברה
    -0.07
    POSITIVE LOGITS
     Fitness
    0.10
     evaluations
    0.10
     expensive
    0.09
     fitness
    0.09
     Bewert
    0.09
     evaluator
    0.09
     Evaluate
    0.09
    评
    0.09
     evaluating
    0.09
     evaluate
    0.09
    Act Density 0.008%

    No Known Activations