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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing thoughts and reflections on personal experiences

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

    now stated facts or observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.71
    الإنجليزية
    -0.66
     estekak
    -0.65
    expandindo
    -0.63
     autorytatywna
    -0.62
    ほうがいい
    -0.61
    ðsíða
    -0.59
    Xpaths
    -0.57
    WireFormatLite
    -0.57
     Meksiku
    -0.57
    POSITIVE LOGITS
     when
    0.51
     since
    0.47
    when
    0.43
    Even
    0.42
    since
    0.42
     even
    0.39
    Since
    0.37
    Especially
    0.37
     lately
    0.36
     now
    0.36
    Act Density 0.034%

    No Known Activations