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

    Neuronpedia

    INDEX
    Explanations

    responses indicating rejection or negative answers

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

    yes/no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SupportActionBar
    -0.43
     inflater
    -0.37
    المشار
    -0.36
    ="'.$
    -0.36
    ())->
    -0.35
     commemorating
    -0.35
     chandelier
    -0.35
    chappe
    -0.35
    arai
    -0.34
    miniature
    -0.34
    POSITIVE LOGITS
    YesNo
    0.68
     betweenstory
    0.62
     Nein
    0.54
    IntoConstraints
    0.52
     preguntas
    0.50
     numberOfRows
    0.50
    הערות
    0.49
     Yes
    0.48
    AsUp
    0.48
    TagMode
    0.48
    Act Density 0.009%

    No Known Activations