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

    Neuronpedia

    INDEX
    Explanations

    .immo, .com URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     âm
    0.73
    IPT
    0.70
     Regardless
    0.67
     Manufacturers
    0.66
    اظ
    0.65
     použ
    0.65
     Personality
    0.65
     Juillet
    0.64
     Persön
    0.64
     Professionals
    0.63
    POSITIVE LOGITS
    asambhavam
    0.65
     प्रतिबंधित
    0.61
    ukary
    0.61
    čen
    0.60
    gever
    0.60
    havam
    0.60
    blob
    0.59
    booked
    0.59
    🏔
    0.58
    abhut
    0.58
    Act Density 0.004%

    No Known Activations