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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Karo
    0.42
    Organization
    0.39
    Td
    0.38
     JMJD
    0.36
     EPFO
    0.36
    庚
    0.36
    НК
    0.35
    Receive
    0.35
    ved
    0.35
    மல்
    0.35
    POSITIVE LOGITS
    牛肉
    0.37
     봅시다
    0.36
     cattle
    0.35
     coaster
    0.35
     صاف
    0.35
     rừng
    0.35
     जाने
    0.34
    стар
    0.34
     precincts
    0.34
    饕
    0.33
    Act Density 0.026%

    No Known Activations