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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs or patterns

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

    Affirmations or confirmations

    np_acts-logits-general · gemini-2.0-flash

    affirmations and confirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.02
    endphp
    -0.88
     '\\;'
    -0.85
    etheless
    -0.84
    '])->
    -0.81
     שוליים
    -0.80
    >*/
    -0.79
    |}{$
    -0.78
     StatefulWidget
    -0.77
    WebServlet
    -0.77
    POSITIVE LOGITS
     inderdaad
    0.77
     @
    0.54
    そうですね
    0.53
    ↵↵
    0.53
    ..
    0.52
     indeed
    0.51
     exactly
    0.50
    !
    0.50
     tatsächlich
    0.49
    ครับ
    0.49
    Act Density 0.553%

    No Known Activations