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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to love and personal connections

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

    Someone should, you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.48
     further
    -0.46
    xaml
    -0.46
    further
    -0.46
    httphttps
    -0.45
    #+#
    -0.42
     additionally
    -0.42
    formik
    -0.41
     rev
    -0.39
    PMailer
    -0.39
    POSITIVE LOGITS
     istrinya
    0.52
     ibunya
    0.49
     Italijanski
    0.48
     spirituale
    0.47
     decât
    0.47
     Paglinawan
    0.47
    */),
    0.44
    IUrlHelper
    0.44
    Beantwoorden
    0.43
     dekorasi
    0.43
    Act Density 0.014%

    No Known Activations