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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a relationship or association between parts or components

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

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.45
    UnknownFieldSet
    -0.39
    lapsingToolbar
    -0.37
    AndEndTag
    -0.36
     ligiloj
    -0.35
     otherwise
    -0.33
    LayoutManager
    -0.33
     Jeg
    -0.32
    paravant
    -0.32
    aulted
    -0.31
    POSITIVE LOGITS
    的一部分
    0.56
     onderdeel
    0.52
     vérit
    0.52
     part
    0.51
    part
    0.50
     часть
    0.49
     ingår
    0.49
    Portion
    0.49
     جزء
    0.48
    Part
    0.47
    Act Density 0.023%

    No Known Activations