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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements and specifications

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

    Text including "sub" followed by a numeral

    np_acts-logits-general · gemini-2.0-flash

    scientific notation with subscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     su
    -0.67
      
    -0.55
     l
    -0.54
     C
    -0.53
     open
    -0.53
     meg
    -0.52
     Su
    -0.52
     \
    -0.52
     “
    -0.51
     h
    -0.51
    POSITIVE LOGITS
     myſelf
    1.29
     purpoſe
    1.23
     Monfieur
    1.21
     Theſe
    1.21
     itſelf
    1.18
     Houſe
    1.17
     Efq
    1.14
     Majefty
    1.12
     pleaſure
    1.11
     ſmall
    1.10
    Act Density 0.018%

    No Known Activations