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

    Neuronpedia

    INDEX
    Explanations

    book titles with "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.62
    -
    0.55
    ۹
    0.53
    9
    0.52
    ř
    0.51
    keletal
    0.49
    ologist
    0.49
    ９
    0.48
    0.48
     &
    0.47
    POSITIVE LOGITS
     μία
    0.49
     एक
    0.49
    <unused654>
    0.48
     μια
    0.47
     করিয়াছিল
    0.46
     a
    0.46
     από
    0.46
    scheduled
    0.46
     혹은
    0.45
    <unused659>
    0.45
    Act Density 0.022%

    No Known Activations