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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences or emotions

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

    including, after, with, the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wicidata
    -0.50
     ویکی‌آمباردا
    -0.40
    WriteTagHelper
    -0.40
     PeEnEo
    -0.39
    jsxFileName
    -0.39
    GenerationType
    -0.39
    enterOuterAlt
    -0.39
    latego
    -0.38
    sätzlich
    -0.38
    Gruss
    -0.37
    POSITIVE LOGITS
     nahilalakip
    0.52
     auroit
    0.49
     MonoBehaviour
    0.44
     Hentet
    0.43
    serialized
    0.40
     StatefulWidget
    0.39
    #![
    0.39
    jure
    0.39
     blind
    0.39
     Moreira
    0.39
    Act Density 0.030%

    No Known Activations