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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate overcoming obstacles or gaps in understanding

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

    remedy or overcome gaps/disadvantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.51
     carreaux
    -0.37
     Controllers
    -0.37
     côn
    -0.37
     controllers
    -0.37
    subsec
    -0.35
     outsource
    -0.35
     уро
    -0.35
     auszu
    -0.34
     Défense
    -0.34
    POSITIVE LOGITS
    setVerticalGroup
    0.53
     ligiloj
    0.50
     старости
    0.48
    EndContext
    0.47
     gaps
    0.47
    ніципалі
    0.47
     AssemblyCulture
    0.46
     устра
    0.45
     Gaps
    0.44
     estekak
    0.42
    Act Density 0.113%

    No Known Activations