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

    Neuronpedia

    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     அத
    -0.09
     تمد
    -0.08
     date
    -0.08
    sson
    -0.07
    nu
    -0.07
     Setting
    -0.07
     apreciar
    -0.07
     отмет
    -0.07
    note
    -0.07
    avent
    -0.07
    POSITIVE LOGITS
     altru
    0.09
     poderosa
    0.08
     মাধ্যমে
    0.08
     poderoso
    0.08
     শক্ত
    0.08
     কেন্দ্র
    0.08
    療
    0.08
     interpersonal
    0.08
     शक्त
    0.08
     Lamb
    0.07
    Act Density 0.013%

    No Known Activations