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

    Neuronpedia

    INDEX
    Explanations

    phrases related to first-time experiences

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

    first post, first time, first public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infór
    -0.47
     становника
    -0.44
     الحره
    -0.43
     myſelf
    -0.43
     pleaſure
    -0.42
    gsmål
    -0.39
     ſtate
    -0.39
     ſta
    -0.38
     trouw
    -0.38
    ništ
    -0.38
    POSITIVE LOGITS
    /**
    0.51
    0.48
    xase
    0.48
     snippetHide
    0.47
    been
    0.46
    0.46
     незавершена
    0.46
     esternos
    0.45
    IsNullOrEmpty
    0.44
    AddTagHelper
    0.43
    Act Density 0.010%

    No Known Activations