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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, acronyms, and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    CU_ or CPL_

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     D
    -0.63
     B
    -0.53
     S
    -0.50
     li
    -0.47
     Ho
    -0.45
     W
    -0.45
     E
    -0.44
     d
    -0.44
     K
    -0.43
     mu
    -0.43
    POSITIVE LOGITS
     Efq
    1.34
     Monfieur
    1.33
     myſelf
    1.27
     itſelf
    1.24
     Мексичка
    1.23
     Jefus
    1.21
    ſelf
    1.19
     whoſe
    1.16
     himſelf
    1.15
     leaſt
    1.12
    Act Density 0.310%

    No Known Activations