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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal attachment or affection

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

    love expressions for things and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.41
    Földrajzportál
    -0.38
    DllImport
    -0.36
    RoutingModule
    -0.35
     ujednoznacz
    -0.35
     posteriormente
    -0.35
    Становништво
    -0.35
    ("")]
    -0.35
    glieder
    -0.35
    xsi
    -0.34
    POSITIVE LOGITS
     love
    1.06
     loves
    1.00
     loved
    1.00
     LOVE
    0.96
    loves
    0.93
     Loves
    0.92
     älskar
    0.91
     Loved
    0.90
     LOVED
    0.88
    love
    0.87
    Act Density 0.013%

    No Known Activations