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

    Neuronpedia

    INDEX
    Explanations

    elements related to conditions and criteria for eligibility in contexts such as trials, legal matters, or organizational roles

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

    contrast or exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.76
     informée
    -0.57
     iprot
    -0.56
    AddTagHelper
    -0.53
    новништво
    -0.52
    writeField
    -0.51
    ſcher
    -0.50
    writeFieldEnd
    -0.48
    rrggbb
    -0.48
    aarrggbb
    -0.47
    POSITIVE LOGITS
     exceptions
    0.59
    除非
    0.53
     Exceptions
    0.52
     exception
    0.52
    However
    0.50
    unless
    0.50
    Exceptions
    0.49
     However
    0.49
    倒是
    0.48
     obstante
    0.48
    Act Density 0.119%

    No Known Activations