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

    Neuronpedia

    INDEX
    Explanations

    references to backs and back-related concepts

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

    body part: back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.71
    ronpa
    -0.67
    Personensuche
    -0.59
    parsedMessage
    -0.57
    tonode
    -0.56
     iNdEx
    -0.56
    ReusableCell
    -0.54
    angliski
    -0.53
    AddHtmlAttribute
    -0.52
    expandindo
    -0.52
    POSITIVE LOGITS
     espalda
    0.86
     backs
    0.85
     Rücken
    0.84
    背
    0.81
     back
    0.79
     sırt
    0.77
    back
    0.74
    Back
    0.73
     Back
    0.72
     BACK
    0.71
    Act Density 0.019%

    No Known Activations