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

    Neuronpedia

    INDEX
    Explanations

    large numerical values associated with significant data points

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

    2 followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endforeach
    -0.51
    ServletConfig
    -0.51
    odi
    -0.49
     ***!
    -0.46
    eti
    -0.46
    indl
    -0.45
    Життєпис
    -0.45
    master
    -0.44
     FIM
    -0.43
    ogi
    -0.42
    POSITIVE LOGITS
     leſs
    0.57
     quæ
    0.56
     anſ
    0.56
     poffible
    0.56
     Relaciones
    0.53
     ſeveral
    0.52
     feroit
    0.51
    حوالہ
    0.51
    ziehungen
    0.50
    Lycka
    0.49
    Act Density 0.037%

    No Known Activations