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

    Neuronpedia

    INDEX
    Explanations

    prime minister or prime numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     greatest
    0.93
     Greatest
    0.88
    Maximum
    0.81
    最好的
    0.79
    نے
    0.73
     phenomenology
    0.72
     finest
    0.72
    ји
    0.71
     maximum
    0.70
    Highest
    0.68
    POSITIVE LOGITS
     minister
    1.66
     Minister
    1.62
     MINISTER
    1.57
     ministre
    1.52
    Minister
    1.40
     ministra
    1.37
     ministers
    1.36
     ministro
    1.34
    minister
    1.32
     وزیر
    1.30
    Act Density 0.108%

    No Known Activations