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

    Neuronpedia

    INDEX
    Explanations

    elements associated with official documentation and identification verification

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

    Japanese words before particles or suffixes

    np_acts-logits-general · gemini-2.0-flash

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -1.15
     
    -1.09
    -
    -0.99
     (
    -0.92
    .
    -0.91
     in
    -0.91
      
    -0.88
     and
    -0.86
     -
    -0.85
    :
    -0.84
    POSITIVE LOGITS
     Efq
    2.20
     myſelf
    2.13
     Monfieur
    2.02
     photolibrary
    1.98
     Reſ
    1.98
     itſelf
    1.97
     Anſ
    1.94
     Majefty
    1.93
     ―――――
    1.92
     ſeveral
    1.91
    Act Density 0.243%

    No Known Activations