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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ActionPerformed
    0.30
     billions
    0.29
     converged
    0.29
     trigonometric
    0.29
    Hvis
    0.28
    Uit
    0.28
    Prime
    0.28
     converging
    0.28
    If
    0.27
    Post
    0.27
    POSITIVE LOGITS
     Sarah
    0.69
     Angela
    0.64
     Maria
    0.60
     Susan
    0.59
     Emily
    0.58
     Rachel
    0.58
     Samantha
    0.57
     Jessica
    0.57
     Jennifer
    0.57
     Lucy
    0.57
    Act Density 0.023%

    No Known Activations