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

    Neuronpedia

    INDEX
    Explanations

    not romantic couples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    जेक्ट
    0.49
    plify
    0.48
    ncies
    0.46
    leşik
    0.46
    wości
    0.45
    eserc
    0.44
    垒
    0.42
    ékony
    0.42
    cale
    0.42
    форми
    0.42
    POSITIVE LOGITS
     eines
    0.48
     fireworks
    0.46
     marriage
    0.43
     tv
    0.43
     couples
    0.42
     eine
    0.41
     mariage
    0.41
     romantic
    0.41
     storms
    0.41
     married
    0.40
    Act Density 0.003%

    No Known Activations